★
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 › Chips › Huawei Ascend 910C

Huawei Ascend 910C

Chip AI Accelerator Shipping

China's frontier chip under sanctions: two 910B dies, SMIC 7 nm, no EUV.

You're looking at a chip record: what this processor is, its key specs, who designs, manufactures and supplies its parts, and where it gets used.

The Ascend 910C pairs two 910B dies to reach roughly H100-class training compute — reported around 800 BF16 TFLOPS — fabricated at SMIC on 7 nm-class DUV multi-patterning because EUV tools are export-banned. Yields and HBM supply are its reported constraints. Huawei's CloudMatrix 384 system lashes 384 of them together with optical links, trading power for scale. Most figures are analyst estimates; Huawei publishes little.

Specifications & key facts

Each figure is labeled by basis: vendor spec, vendor claim, reported, estimate, or official. "Not publicly disclosed" means exactly that — we never invent values.

Overview

Designer Huawei (HiSilicon)
Status Shipping in China; export-restricted supply chain

Manufacturing

Foundry / process SMIC 7 nm-class (DUV multi-patterning)Reported

Compute

BF16 ~800 TFLOPS (dual-die)Estimate

Memory

Memory 128 GB HBM2E (8 stacks, dual-die)Estimate

Physical

System CloudMatrix 384: 384 chips, optical interconnect, ~560 kWReported

How this connects to the rest of the stack

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

Designed by

Manufactured by

Competes with

Sources

SemiAnalysis on CloudMatrix (April 2025) ↗

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