DLC vs immersion cooling for AI data centres

COMPARISON · AI DATA CENTRE COOLING

Direct-to-chip liquid cooling vs immersion cooling for AI

Direct-to-chip liquid cooling (DLC) and immersion cooling are the two primary architectures for AI-density thermal management above 30-40 kW per rack. DLC uses cold plates + cooling distribution units (CDUs); immersion submerges hardware in dielectric fluid (single-phase oil or two-phase fluorinated). Both persist because they solve different constraints. DLC dominates GPU-training clusters and is easier to retrofit; immersion offers higher volumetric density and simpler thermal management for extreme-density edge cases.

01Bottom-line verdict

Both persist. DLC for hyperscaler GPU-training + retrofit-heavy contexts. Immersion for ultra-density new-build + specific niche applications. The dominant AI-density greenfield is DLC. Immersion is the fastest-growing but from a small base. Fluid supply (two-phase fluorinated) is a specific supply-chain constraint for immersion at scale.

02Comparison table

Direct-to-chip (DLC)Immersion (1-phase + 2-phase)
ArchitectureCold plates on GPU/CPU + CDU + secondary loopServers submerged in dielectric fluid
Density supportedUp to ~600 kW per rack demonstratedUp to ~1000 kW per rack in dense configurations
Retrofit into existing rack formsStraightforward with cold plate + CDURequires immersion tank; not rack-form-compatible
Fluid choiceWater-glycol or dielectric coolantSingle-phase: mineral or synthetic oil. Two-phase: fluorinated (3M Novec, Solvay Galden)
Vendor concentrationCoolIT (Ecolab) + Motivair + Asetek + BoydSubmer + LiquidStack + GRC + Iceotope
Hyperscaler adoption (2026)Meta, MSFT, GOOG, AWS AI clusters using DLCGrowing but smaller absolute footprint
Fluid supply chainWater + coolants: broad, low-riskTwo-phase fluorinated: concentrated (3M, Solvay), PFAS-adjacent regulatory pressure
Maintenance accessStandard rack access, hot-swap possibleTank access; harder to service individual components
OCP standards supportAdvanced Cooling Solutions workstreamAdvanced Cooling Solutions workstream
Capex per MW cooling~$1.2-1.5M/MW for greenfield DLC~$1.5-2M/MW single-phase; higher for two-phase

03Decision framework

Choose Direct-to-chip (DLC) when

  • Density 40-500 kW/rack. DLC covers the mainstream AI-density band
  • Retrofit of existing air-cooled facility. Cold plates + CDU integrate into existing rack forms
  • GPU-training cluster (Meta, MSFT, GOOG, AWS pattern). Reference deployments are DLC
  • Serviceability priority. Standard rack access preserved
  • Fluorinated fluid supply concerns. Water + glycol coolants are unconstrained

Choose Immersion (1-phase + 2-phase) when

  • Ultra-density new-build (>500 kW/rack). Immersion volumetric density can exceed DLC at extremes
  • Extreme-ambient siting (desert, tropics). Immersion thermal envelope more permissive
  • Specific accelerator packages designed for immersion. Some ASICs + custom silicon optimised for immersion
  • Sound-sensitive locations. Immersion runs quieter (no rack fans)
  • Willing to underwrite fluid supply-chain risk. Two-phase fluorinated requires supply-chain diligence

04Deep-dive research

05Primary sources

06Frequently asked

When is air cooling still viable for AI?

Below ~30-40 kW/rack sustained. Above that, air-cooling infrastructure scales sub-linearly in cost + energy compared to liquid alternatives.

Why is two-phase fluorinated fluid a supply concern?

Manufacturing capacity for specific fluorinated fluids (3M Novec, Solvay Galden) is concentrated among a small number of chemical suppliers, some facing regulatory pressure on PFAS/fluorochemistry. Growth in immersion demand could outpace fluid supply expansion.

Can I mix DLC + immersion in one facility?

Yes, common in newer facilities to allocate DLC for GPU-training and immersion for specific edge-case density zones.

What is the biggest vendor-side risk in DLC?

CDU + high-current disconnect connector reliability, specifically for hyperscaler-scale deployments. Fewer failure points than immersion but each failure is more consequential.

Definition Direct-to-chip liquid cooling (DLC) circulates single-phase coolant through cold plates mounted on the CPU/GPU package, while immersion cooling submerges servers in dielectric fluid. Both are used for AI data centres above 100 kW per rack where air cooling cannot sustain thermal removal.
Direct-to-chip vs immersion cooling comparison
DimensionDirect-to-chip liquid cooling (DLC)Single-phase immersionTwo-phase immersion
Thermal capacity per dieUp to 1,500W per dieUp to 400W per dieUp to 2,000W+ per die
Coolant typeWater-glycol mix (facility loop) + dielectric secondarySynthetic hydrocarbon dielectric (mineral oil, PAO)Fluorocarbon dielectric (boiling at ~50°C)
Server modification requiredCold plate + hose fittings onlySealed / dielectric-safe serverSealed / dielectric-safe server
Hyperscaler deployment status (2026)Broad: Meta, Microsoft, Google, OracleLimited: bespoke deploymentsEmerging: OCP Sustainability Project
Top vendorsCoolIT (Ecolab), Motivair (Schneider), Vertiv, Boyd (Eaton)Submer, GRC, LiquidStackLiquidStack, ZutaCore, Iceotope
Chemistry supply chain riskLow (water-glycol widely available)Medium (single-source dielectrics)High (PFAS regulatory pressure)
CDU + secondary loopRequired for chip-package coolant separationNot requiredNot required
Best fitRack retrofit + hyperscale greenfield 50-500 kW/rackEdge + specialist AI workloads1,500W+ per die (Rubin Ultra, custom silicon)