Foundry · Company record
SMIC
AI chips fabricated at SMIC per public disclosures. As of 2026-08-25, 3 chips across 1 designer.
Huawei3 chips
- Huawei Ascend 910B
Huawei's flagship domestic AI training accelerator, positioned as the primary Chinese alternative to Nvidia H100 after US export controls. Uses HBM3, Da Vinci architecture. Widely deployed at Chinese hyperscalers and government cloud regions.
- Huawei Ascend 910C
Follow-on to 910B (2024), targeting ~60% of H100 training throughput on Da Vinci 3.0. Volume production ramping despite HBM supply constraints from Samsung/SK Hynix export restrictions.
- Huawei Ascend 910D
Announced 2025 as the next generation targeting Nvidia B200 territory. Chiplet architecture per public disclosures; volume production timeline uncertain given SMIC 5nm-equivalent process constraints.
Rebuilt every 15 minutes. Chip → foundry map is hand-maintained in src/services/chips.ts. See every tracked foundry or every AI chip on record.