Huawei's Ascend 960 to debut LogicFolding architecture amid memory reallocation clues
GlennLuk · x · 2026-09-17
Chip watchers unpack why Huawei's Ascend 960DT got pulled forward:
- The 960 will be the first AI accelerator to use Huawei's LogicFolding architecture, after the Kirin 950 Pro mobile SoC — a notable confidence signal given AI accelerators' far larger die, packaging, and power demands
- @gpuhell's theory: with the 950DT not yet ramped this year, the only sensible explanation for the acceleration (Q3 2027 → Q1 2027) is that LogicFolding works well enough to shift memory chips allocated for the 950DT to the 960DT
- GlennLuk adds: the timeline move also signals confidence in domestic HBM and DUV scanner supply despite 2024 export controls
Related event: Huawei Unveils Ascend 960 and UnifiedBus for Million-Chip Clusters(4 posts)→
More from Infra
- Scotland pauses new data centre approvals for a year; Australia urged to follow — TobyWalsh · 2026-09-17
- huggingface_hub 1.32 lets UV scripts declare runtime images for HF Jobs — vanstriendaniel · 2026-09-17
- Open-sourced Qwen-1B-RLCD runs type-safe JSON inference 5x faster on-device — JiliJeanlouis · 2026-09-17
- Fathom Speeds Million-Token KV Scans 1.67x with Per-Query Read Depth — Vivek Kalyanarangan · 2026-09-17
- Edge0 Streams a 35B MoE from SSD at 20 tok/s on a Single 24GB GPU, Open Source — Edge0 · 2026-09-17
- Daytona Benchmarks NVIDIA Vera CPU on Agentic Workloads, Cited in Official Blog — mattturck · 2026-09-17