★
Menu
Home How It's Built Watchlist The Stack
Hardware ChipsCompare Chips Servers & SystemsNetworking MemoryFoundries & Packaging Cooling
Facilities Data CentersPower ProjectsCloud & GPU Compute
Intelligence AI ModelsSoftware AI ProductsBenchmarks Research PapersDatasets Concepts
Ecosystem CompaniesStocks PeopleTimeline TrendsFuture of AI
Learn News Ask the Data AI Agents
About About us Methodology Data & API Disclaimer
Options
DATA & API

Free read-only JSON access to the site's cached data.

Dark mode

Guided View
New to chips, data centers and model jargon? We explain key terms as you browse, in plain English. Same data, with the help built in.

Expert View
You already know the stack. Just the data: clean, fast and compact, with no extra explanations. This is the default view.

Interface language
‹ Back
Home › Technologies › Direct-to-Chip Liquid Cooling

Direct-to-Chip Liquid Cooling

Technology Cooling

Cold plates on every die — mandatory at Blackwell rack densities.

You're looking at a technology record: a building block of AI hardware — what it does, who makes it, and which chips and systems use it.

Direct-to-chip cooling pumps treated water through cold plates bolted onto GPUs, CPUs and switches, then rejects heat through rack manifolds and coolant distribution units. GB200 NVL72 made it mandatory at the frontier: roughly 1.5-2x the heat per rack that air can practically remove, at far better efficiency. The retrofit and new-build wave behind it powers Vertiv, CoolIT, Boyd, Motivair and peers.

How this connects to the rest of the stack

This record's links at a glance — click a group to jump to it.

Successor to

Competes with

Sources

OCP cooling projects ↗

Record reviewed as of 2026-01-15 — see Methodology.