Immersion Cooling (Single-Phase & Two-Phase)

Immersion cooling looks like the technology that should have won if heat capture were the only score. It is not the only score, because the rack’s service boundary moves into a fluid bath. Submerge the whole board in a dielectric bath and you remove every air gap, every fan, the external cold-plate interface, while retaining the package and component-to-fluid resistance. The thermodynamics are excellent: high heat capture, halls quieted by removing server fans, and a concentrated warm fluid stream ready for heat reuse when the selected fluid and exchanger carry the duty; pumps and rejection fans still spend energy and make noise. For a decade the cooling roadmaps drew immersion as the inevitable endpoint past the air-cooling cliff. As of 2026 that endpoint has not arrived, blocked not by thermodynamics but by chemistry, serviceability, supply chain, and insurability. The frontier racks of 2025-2026 are cooled by direct-to-chip liquid, not by tanks. → Chapter 5.4.

This chapter weighs a technology you may correctly choose not to deploy. The two architectures that get lumped together are single-phase immersion (the fluid stays liquid, pumped past the boards) and two-phase immersion (the fluid boils on the hot components and condenses on a coil), and their 2026 maturity differs sharply. Single-phase is a viable, supply-secure niche. Two-phase remains qualification-constrained: 3M exited PFAS manufacturing, while Chemours' Opteon fluid has been qualified in current-generation 2CRSi servers. The forks ahead are immersion vs direct-to-chip at the architecture level and single- vs two-phase within immersion, and each carries downstream costs: capex, serviceability MTTR, floor loading, PFAS liability, and the insurance/fire-suppression posture that quietly gates whether a lender or insurer will let you build it at all. → Chapter 2.6, Chapter 6.5.

Both architectures drop servers — de-fanned, with thermal-interface material swapped for immersion-grade compound and any spinning disks replaced by flash — into a dielectric fluid that is electrically non-conductive, so live boards sit safely submerged. The difference is what the fluid does with the heat.

Single-phase immersion keeps the coolant liquid throughout. A pump circulates a synthetic hydrocarbon or fluorinated oil through the tank and across a liquid-to-liquid heat exchanger that hands the heat to the facility water loop. The single-phase bath can tolerate open-tank access and routine service when its qualified fill, temperature, fire classification and handling procedure permit it; the fluid and hardware set those limits, and a low fill that uncovers a hot component is no longer forgiving. Heat transfer is by forced convection, so the density ceiling is set by how much fluid you can pump and how warm you let it run — strong, but not unlimited. Operationally it behaves like a very wet rack: contained, manageable, serviceable with gloves and a drip tray.

Two-phase immersion exploits the latent heat of vaporization. The fluid is engineered to boil at a low temperature (typically ~49–60 °C) right at the hot components; the rising vapor carries enormous heat flux per unit area, condenses on a chilled coil at the top of a vapor-managed bath, and rains back down. Boiling heat transfer is far more aggressive than convection, which is why two-phase can buy heat-flux headroom with less circulation, provided the boiling surface, condenser and vapor system close the duty; count their total auxiliary input before declaring an energy winner. But it demands a vapor-management enclosure, a fluid with an exactingly tuned boiling point, and tight vapor control — and that fluid, until 2025, came almost exclusively from one place.

Chemours’ February 24, 2026 announcement reports Opteon 2P50 qualification in 2CRSi’s Atlantis and Octopus server work, followed by a joint development agreement. That supports the named immersion-fluid/server scope. The agreement’s wider direct-to-chip development objective is not certification of another cold plate, fluid formulation or delivered product.

The table can invert the old cooling scorecard. A bath that wins on heat capture can still lose when the operator prices capex, serviceability, fluid supply, OEM warranty and insurability. Removing server fans does not remove pumps, condensers, fluid handling or GPUs idle during service. Direct-to-chip can win through tray access and common spares; immersion can win when its heat capture, environmental isolation and service design repay the tank and fluid costs. The obstacle is often the operational and institutional friction wrapped around the cooling. Compare it on one operating brief: an unmatched cooling-system PUE or equipment-only price cannot pay that bill.

The most underestimated cost of immersion is the labor and downtime of touching the hardware, not the fluid. A direct-to-chip rack services like a conventional rack: pull a tray, the dripless quick-disconnects seal, swap the part, reinsert. An immersion tank does not get hot-swap merely by staying powered: define which server can be isolated and lifted while the remaining bath stays in service. To replace a failed DIMM, NIC, or — most commonly — a GPU, a technician hoists the entire server out of the bath on a lift, lets the fluid drain (single-phase) or manages vapor escape (two-phase), works on a dripping board over a containment tray, and re-immerses. A simple component swap in a tank can mean drain, dry, work the board, refill and recondition, where the selected tank procedure requires those steps; the air-cooled comparison starts with the same failed assembly, spare and crew. Time diagnosis, isolation, extraction, fluid recovery, checks and workload restoration before planning an SLA around the difference. The procedure decides whether one server or the whole bath is unavailable; a task estimate is not fleet MTTR.

That tax compounds against the failure rate of the fleet it is cooling. A GB200-class rack is 72 accelerators each dissipating ~1 kW+; at frontier scale, GPU and optics failures are a daily fleet event, not an annual one. Multiply an hours-not-minutes service time by a high failure cadence and the goodput cost — GPUs idle while a tank is opened, drained, and re-sealed — becomes the dominant operational argument against immersion for training fleets, where every node-hour lost is a job-wide straggler or a checkpoint restart. The cooling that minimizes PUE can maximize the time a failed node spends out of service. For a power-bound operator paying for every megawatt, idle accelerators in a tank are the worst kind of stranded capacity. → Chapter 5.4 on the serviceability advantage of cold plates.

Immersion inverts the floor-loading conversation. Direct-to-chip adds on the order of ~100–300 kg per rack (manifolds, tray loop assemblies, and the in-rack fluid charge) — the full support and move-route check must include the cooling hardware; it is the dense rack itself that forces the structural look (Chapter 5.10). A flooded immersion tank is a different object: the cited Vertiv tanks have fully loaded masses of 1,732–2,095 kg, and the CDU/filtration skid adds a separate load. The manual's 1,679–1,721 kg/m² values are footprint-average screening pressures without support frames, not leg or frame reactions. Those screens can exceed an area-average floor criterion, which means immersion frequently forces a slab-on-grade design or structural reinforcement — a decision that belongs at scoping, not at install. A hall that pencils out for air or DLC may simply be unable to host a tank farm without re-pouring concrete.

This is why immersion is overwhelmingly a greenfield, purpose-built decision rather than a retrofit one. The combination of multi-ton equipment masses and project-specific support reactions, low horizontal tanks that consume floor area differently than vertical racks, the fluid storage and handling infrastructure, and the suppression/containment requirements rarely fits a brownfield hall designed for vertical air-cooled cabinets. The retrofit path past the cooling cliff often favors rear-door heat exchangers or direct-to-chip when a tank would need a new support frame, move route, handling area or fluid store; keep the tank in the comparison where its actual reactions and service space fit, and price the enabling works where they do not. → Chapter 5.4.

Immersion is niche, not dead, and there are real workloads where it remains the right answer. Heat reuse is its strongest case: single-phase immersion delivers a clean, warm, single-stream fluid that is unusually well-suited to feeding a heat pump and a district-heating offtake. Because the whole board sits in the fluid, there is no parasitic air load to dilute the return temperature, and the heat comes out as one coherent stream rather than split between a liquid loop and a residual air loop the way a DLC+RDHx rack does. Where a district-heating network or an industrial offtake exists, immersion's heat-reuse quality can flip its economics. → Chapter 5.9 (engineering) and Chapter 15.5 (economics/district heating).

The other durable niches are extreme-density and harsh-environment deployments: cryptocurrency mining (where density-per-dollar dominates only after the actual service cost and production lost during repair are counted), space- or dust-constrained edge sites where a sealed tank beats trying to filter and condition air, and specialized HPC where the thermal headroom past direct-to-chip is genuinely needed today. As rack densities climb toward the 600 kW Kyber/Rubin-Ultra generation and beyond — where even direct-to-chip is approaching its single-phase limits — immersion's latent-heat headroom may re-enter the mainstream conversation, but only if a supply-secure, insurable two-phase fluid (or a sufficiently aggressive single-phase design) is available. The bet immersion is making is that the density ramp eventually outruns what cold plates can do. → Chapter 5.1 (the density wall) and Chapter 16.2 (subsystem roadmap).

A constraint that rarely appears in cooling-technology comparisons but routinely decides them is whether the facility is insurable and code-compliant. A large open tank of dielectric fluid is, to a fire authority and an insurer, a fuel load and an unusual suppression problem — even when the fluid's flash point is high. Conventional rack-based suppression (clean-agent or pre-action sprinkler) does not map cleanly onto a tank farm; immersion changes the fire model, the containment requirement, and the spill-response plan. Two-phase requires a vapor-management enclosure; whether it is a code pressure vessel follows the named system's MAWP, construction, fluid, and local code, while PFAS handling is a separate fluid-specific diligence item.

The consequence is that immersion can fail a project not on engineering but on diligence: an insurer (FM Global-class) or lender declines to underwrite a novel cooling architecture with thin actuarial history, or a local authority having jurisdiction will not sign off on the suppression scheme. This gate is often the real reason a board-approved immersion pilot never scales — the technology works, but the risk-transfer and life-safety paperwork does not close. Engage the insurer and the AHJ before committing white space, not after. → Chapter 6.5 (fire detection, suppression & life-safety) and Chapter 2.6 (insurance & risk transfer).

Cold-plate allowance = 20 + 25 + 25 = 70 minutes; immersion = 20 + 30 + 25 + 35 = 110 minutes. Both fit the 180-minute ceiling, and both are far shorter than the source-modeled 6–12 hours per immersion component swap against 30–60 minutes on air, because this case grants an on-site qualified spare and a trained crew. Retain both candidates for the matched thermal and lifecycle-cost comparison; the shorter procedure alone does not price recovery of a distributed job.

The immersion design has 70 minutes of remaining allowance. A missing qualified spare that adds 90 minutes produces 200 minutes and fails by 20. Stock the spare or change the service design. Acquire a timed demonstration and warranty confirmation before treating either allowance as an accepted restoration time. OCP qualification and service interfaces provide context; 14.5 owns the operating procedure and 13.5 its cooling acceptance handoff.

Choose immersion when its qualified hardware and fluid, wet support reactions and demonstrated service process meet the same duty and restoration contract as the alternative. A lower auxiliary load has no operational value if the supported replacement workflow misses the required restoration window.