Direct-to-Chip Liquid Cooling (DLC) — Architecture, Fluid & Thermal Design

By 2026 the argument about whether AI racks need liquid is over. GB300 NVL72 shipped in 2025 and deploys through 2026 alongside GB200; Lenovo specifies 135 kW rack TDP and up to 155 kW peak. The best-documented published heat split is still the cited HPE GB200 NVL72 record, which assigns roughly 115 kW to liquid and 17 kW to residual air (Chapter 5.2); this chapter derives from that record and scales to the rack you name. That product-specific heat split makes direct-to-chip liquid cooling (DLC) plus residual room-air removal the supported basis; Chapter 5.1 explains the wider selection envelope. Rear-door heat exchangers and air-assisted liquid (Chapter 5.3) extend a brownfield envelope only where the named product rating, airflow or room-rejection path, water conditions, service/redundancy case, and refresh tail close. For a greenfield whose selected or roadmap rack profile requires liquid capture at source, DLC and its residual-air path belong in the design basis before steel is cut. For VR200 NVL72, size irreversible infrastructure to NVIDIA's 330 kW cabinet TDP facility design basis and run energy and TCO models on Pegatron's 188 kW Max Q / 228 kW Max P operating profiles; NVIDIA reported Vera Rubin in full production in August 2026.

Once DLC is assumed, the decisions that remain are concrete. Choose two-phase with a refrigerant that meets the applicable PFAS definition and you inherit that supply-chain and liability problem alongside the pressure, vapor and OEM-support obligations. Choose hand-mated flexible hoses over blind-mate manifolds and you trade factory-aligned tray geometry for field access and routing freedom — and a different leak-risk profile; either can self-seal, so qualify spill, cycle life and air inclusion for the actual service procedure. Budget the cold-plate delta-T too tight and you over-spec the CDU and the pumps; too loose and you throttle the GPUs. Each of these forks is cheaper to see before it is poured into a slab.

A direct-to-chip cold plate is a sealed metal block — typically copper, sometimes copper-on-aluminum — pressed onto the die package through a thermal interface material (TIM), with coolant forced through internal microchannels or skived fins directly over the hot silicon. The heat path is short and the thermal resistance low: a few hundredths of a °C per watt from junction to coolant, which is what makes 1.0–2.3 kW per GPU package tractable. The first fork is whether the coolant changes phase inside the plate.

Single-phase cold plates keep the coolant liquid throughout. A water/glycol mix enters, warms by a bounded delta-T (commonly 7–12 °C), and leaves still liquid. Heat removal scales with mass flow times specific heat times delta-T — pump harder or run a wider delta-T to carry more watts. It is mechanically simple, the fluids are benign (water-based, non-PFAS), the pressure regime is well understood, and it maps cleanly onto the CDU-and-secondary-loop architecture of Chapter 5.6. The penalty is that water has finite heat capacity, so very high heat fluxes demand high flow and therefore pump energy and pressure drop.

Two-phase cold plates exploit the latent heat of vaporization: a low-boiling-point dielectric enters as liquid, boils inside the plate, and leaves as a vapor-liquid mixture. Because latent heat dwarfs sensible heat, two-phase moves enormous heat flux at low flow and a nearly isothermal plate surface — a thermally attractive candidate for the 1.5–2.3 kW package design problem when its component temperature, flow stability and rejection conditions beat the supported single-phase alternative. The catch is the working fluid. The engineered dielectrics that boil at convenient temperatures have so far included fluorochemicals in the PFAS family under the broad EU proposal’s definition, and that is a regulatory and liability exposure rather than a footnote; the 2026 HFO alternatives are fluorinated too, so qualify the named fluid’s composition, warranty and supply instead of trusting the phase label.

Getting coolant from the rack inlet to 72 cold plates and back, while letting a technician swap a failed tray in minutes without draining the rack, is the second major fork in DLC design. Every NVL72-class rack carries a vertical pair of manifolds (a supply and a return rail, the in-rack analogue of a busbar) running the rack height. Each compute tray taps the rails through couplings. The decision is what kind of coupling, and it trades serviceability against reliability and leak risk.

Blind-mate / floating-tray couplings are integrated into the tray and the manifold so that sliding the tray home automatically engages the fluid connection — no hose to route, no fitting to hand-torque. The 'floating' geometry absorbs the mechanical tolerance stack so the connection self-aligns. This is the factory-integration path: couplings are validated at L10/L11 integration (Chapter 5.13 on the mechanical side; rack integration in Part 7), and field service becomes a slide-out/slide-in operation. The cost is rigidity — the rack and tray geometry are co-designed and far less forgiving of field improvisation.

Hand-mated flexible-hose quick disconnects put a short hose with a dry-break coupling between the tray and the manifold. The technician physically connects two halves; the dry-break valve seals both sides on disconnect so the spill is bounded to the qualified small release rather than an open stream, with both spill and air inclusion checked at the specified pressure and cycle count. This is more serviceable in the messy reality of a live hall and tolerant of tolerance stack-up, but every manual connection is a potential leak point and a human-error surface, and the hoses add pressure drop and clutter. OCP has standardized UQD form factors precisely to make these field-mateable and second-source-able.

Require the supplier to identify the exact connector, manifold and rack-interface revisions and the tested mating pair. The OCP Cold Plate index separates accepted contributions from work in development; the Open Rack index identifies the rack documents. An OCP interface name does not establish cross-vendor interchangeability, seal compatibility or warranty. Freeze those interfaces in the purchase schedule and rehearse the actual tray replacement before approving the service boundary.

The thermal budget is governed by one conservation equation: the heat a loop carries equals mass flow times specific heat times the coolant temperature rise (Q = ṁ · cp · ΔT). Everything in DLC design is a negotiation among the three terms on the right — and against a pressure-drop ceiling that the pumps and CDU must overcome.

Flow from the heat balance. Use Q = ṁ·cp·ΔT on the liquid-captured heat. For water-like properties, 1 kW at a 10 K rise requires about 1.43 L/min; recalculate with the approved fluid at its operating temperature. For the HPE GB200 NVL72's ~115 kW liquid share, water-property illustrations are about 82 L/min at 20 K, 165 L/min at 10 K, and 236 L/min at 7 K. A Dober PG25 planning illustration of roughly 1.25–2.0 L/min/kW at 7.5–12 °C is supplier guidance, not an OCP or OEM acceptance requirement. Size the manifold and CDU from the named vendor schedule or declared-fluid calculation plus the pressure and control margin. Run a wider delta-T and you cut the flow (and pump energy) for the same watts — but you raise the return-water temperature the heat-rejection plant must handle and you push the warmest cold plates closer to the throttle line.

Wide vs. tight delta-T. A wider coolant delta-T is a gift to the facility: it means less flow, smaller pipes, lower pump energy, and warmer return water that free-cooling and heat-reuse plants love (Chapter 5.7, Chapter 5.9). For the cited QCT GB200 NVL72 reference, 45 °C maximum liquid inlet and 65 °C maximum liquid return are separate limits, not a prescribed 20 K operating rise; ASHRAE W45 describes FWS supply capability. The junction budget still binds: the delta-T you can run is bounded by the supply temperature plus the cold-plate's thermal resistance, so spend the budget on a wide delta-T at a warm inlet and the last plate in a series path may sit too warm. Design teams therefore favor parallel manifold paths so every cold plate sees near-inlet coolant. Series routing cuts the total flow the manifold must carry and simplifies the run, but plate pressure drops add along the string and every downstream chip starts warmer — so choose it only where both the required head and the last plate's junction temperature still close at the named per-plate flow.

Pressure-drop budget. Pump head is divided among the selected cold-plate pressure-flow curve (including declared fittings and quick disconnects), the in-rack manifold and headers, and the secondary loop back to the CDU. Rack-level pressure drop runs through the headers, hoses, QDs and cold plates on the limiting parallel path; use the assembly pressure-flow curve and name what it includes, or counting the same loss twice will oversize the pump. Every fitting, every hose, every reduction in channel size buys lower thermal resistance at the price of more pressure drop — and pressure drop is pump energy, which shows up in PUE. The cold-plate designer's lever — finer microchannels for lower thermal resistance — is exactly the lever that raises pressure drop, so the per-chip design is an explicit optimization of thermal resistance against pressure drop.

Parallel routing needs 4.00 L/min at 20.0 kPa plate-path loss. Both junctions are 35.0 + 1,000 × 0.0400 = 75.0 °C, retaining 10.0 K. Series needs 2.00 L/min at 40.0 kPa; the first plate raises water temperature by 1.00 × 60/(2.00 × 4.18) = 7.18 K, so the second junction is 82.2 °C and retains only 2.82 K. Choose parallel to preserve the required reserve. Ideal plate-only hydraulic power is 1.33 W in either arrangement; pump efficiency and external losses decide electrical input.

The series choice reverses at supply ≤85.0 − 5.0 − 40.0 − 7.18 = 32.8 °C, calculated without intermediate rounding. Colder supply spends rejection opportunity to avoid extra header flow. Alternatively, qualify a different component/plate duty. OCP’s cold-plate method keeps the coolant-inlet reference explicit; use 5.1 for the thermal method and 5.13 for the complete hydraulic selection.

'Liquid-cooled' overstates what DLC does. On the GB200/GB300-class racks documented here it cools the high-flux components only — the GPUs, the CPUs/Grace dies, the NVLink/NVSwitch silicon, and increasingly the high-power VRMs — leaving a residual air load that a hall ignores at its peril. On a GB200 NVL72 rack, roughly 115 kW is removed by liquid and ~17 kW remains on air — about 13% of the rack. Scale the split with the rack you name: GB300-class racks run higher total power and a higher liquid duty, so an air tail sized off the GB200 record is sized for the previous generation — and the tail is not permanent, because NVIDIA's Vera Rubin generation is specified fully liquid-cooled with the rack fans removed and the NICs, optics and power boards on the loop (Chapter 5.2). That tail is everything not worth a cold plate: NICs and optical transceivers, DIMMs, power-supply units, lower-power voltage regulators, the BMC, and miscellaneous board components. Optics in particular are a growing concern — pluggable transceiver power is climbing, and the optics sit at the rack's air-cooled edge precisely where airflow is now sparse.

The fork here is how you capture the air tail. Three patterns dominate. In-rack air-to-liquid: a small rear-door or in-chassis air-to-liquid heat exchanger rejects the residual air load back into the same liquid loop, so the rack exhausts neutral air and can make a ‘zero-air-to-room’ rack possible when coil temperature and airflow close; the hall needs no separate mechanical air plant only if another sink or demonstrated heat reduction covers the required failure-state duty. Hybrid containment: the hall keeps a reduced CRAH/in-row air system sized only for the ~10–20% air tail, with hot/cold-aisle containment, which is simpler to retrofit but reintroduces an air plant and its PUE. Facility air: let the tail dump into the room and pay for the building air system to catch it — distribution, installed capacity and degraded operation must close at the actual rack count; compare that plant cost with rack coils. A hall that sizes liquid for 115 kW and forgets the 17 kW air tail will thermally throttle on the optics and DIMMs while the GPUs run cold — stranding the rack it just paid to liquid-cool. → containment strategy for hybrid halls in Chapter 5.3; Chapter 8.3 qualifies the populated switch and port-bank cooling envelope; 8.9 owns optical-channel qualification and 8.10 the packaging and replaceable-part boundary. Liquid cooling of a switch ASIC does not qualify its faceplate optics.

Cold plates have a hard physical limit: no matter how good the plate, heat must still conduct from the junction, through the package, across the TIM, and into the plate before the coolant ever sees it. That stacked thermal resistance — and especially the TIM — is what caps the flux a cold plate can handle. The next step removes the intermediary entirely: etch the coolant channels into the silicon itself.

In-chip (direct-to-silicon) microfluidics routes coolant through microscopic channels — each roughly a hair's width — cut directly into the die or the backside of the package, so liquid flows over the hotspots inside the chip rather than across an external plate. Microsoft's 2025 prototype, using AI-designed, leaf-vein-inspired channel networks, reported up to 3x better heat removal than state-of-the-art cold plates and up to 65% lower peak temperature rise. The rationale is pure thermal resistance: collapsing the conduction path from junction to coolant is the only way to keep pace with 3D-stacked dies and the projected 2–3 kW packages behind them, where a cold plate simply runs out of room. Treat it as a roadmap signal rather than a 2026 production technology. The full consolidated cooling roadmap, including immersion's role and the 600 kW–1 MW rack generation, lives in Chapter 16.2.

Choose the plate topology, connection interface and service isolation together. Series plumbing saves flow only while the downstream component retains its margin; parallel plumbing spends distribution capacity to preserve a common inlet. Release procurement against the complete supported assembly and its qualified operating point.