COMPUTE ATLAS Supercomputer supply-chain graph
1153 systems 482 sites Sourced data

Supercomputers/Systems/Huawei Cloud Ulanqab CloudMatrix Supernode

China · operational · mixed

Huawei Cloud Ulanqab CloudMatrix Supernode

Also known as Huawei Cloud Ulanqab Data Center CloudMatrix 384

Operated by Huawei at Huawei Cloud Ulanqab Data Center .

Phase 1 seed dataset, compiled by hand. These rows were built from public operator, laboratory and vendor sources. A mechanical second-reader pass has since fetched every cited source: 1092 of 1153 systems have a readable citation that names them, and 40 are genuinely weakly sourced. Every claim carries its source and a confidence tier. Treat anything below verified as a lead, not a citation.

Measured performance

Rmax
-
Rpeak
-
Rmax ÷ Rpeak
-
Cores
-
Power
-
Per watt
- GF/W

Figures are as last publicly reported for the configuration described below, not a live measurement. Where a system was upgraded in place, the post-upgrade configuration is shown and the earlier one appears in the timeline.

What this machine is made of

One row per supplier relationship. “Supplier at build” is the company that shipped the part at the time; where that company has since been acquired, the parent it rolls up to today is shown beside it. That distinction is what makes ticker-level aggregation possible across a thirty-year dataset.

Role Part Supplier at build Quantity Confidence Source
Integrator -
Huawei Cloud deployed and operates the CloudMatrix 384 supernode at its Ulanqab data center
Huawei
- Reported chinaresearchcollective.substack.combaike.baidu.com
Accelerator Huawei CloudMatrix 384
Accelerators
Da Vinci
Huawei CloudMatrix 384 supernode, 384 Ascend 910C NPUs; number of supernodes at Ulanqab not stated
Huawei
- Reported chinaresearchcollective.substack.combaike.baidu.com
CPU -
192 Huawei Kunpeng CPUs per CloudMatrix 384 supernode
Huawei
- Reported chinaresearchcollective.substack.com

The read

Huawei Cloud's CloudMatrix 384 supernode deployment at its Ulanqab, Inner Mongolia data center. A China Research Collective analysis says the supernode, released in April 2025, was first deployed at the Ulanqab data center and that a June 2026 full-parameter post-training of a DeepSeek V4 Pro model ran on it; Baidu Baike lists Ulanqab alongside Wuhu and Gui'an as deployment sites. A supernode is 384 Ascend 910C NPUs and 192 Kunpeng CPUs in 16 racks; the analysis estimates 350 to 500 kW per supernode, which Huawei has not published. The number of supernodes at Ulanqab is not stated, so no site-level FLOPS, power or accelerator count is recorded. The claim that Ulanqab was the first site conflicts with Light Reading's report of Wuhu running in April 2025, so confidence is reported.

Timeline

Site & facility

Change history

Source check

We fetched this system's own citations and recorded whether each page actually mentions it. This is a corroboration signal, not a fact check, and it is published so you can see how well the sourcing holds up rather than take it on trust.

Cited sourceResultFound on the page
baike.baidu.comnames system and partHuawei CloudMatrix 384
chinaresearchcollective.substack.comnames system and partHuawei CloudMatrix 384

Checked 2026-10-09 by pnpm verify. Re-run it and the table changes with the web.

Further reading