960DT is set to arrive early, boasting performance far exceeding anything the West could offer the Middle Kingdom.
At its annual Connect conference, Huawei unveiled a new generation of AI accelerators that promise performance far beyond anything Nvidia can now sell in the Middle Kingdom.
If that weren’t enough, the chip, codenamed the Ascend 960DT is slated to arrive a full three quarters ahead of schedule, launching in the first quarter of 2027.
Compared to American GPUs, the 960DT offers similar memory and bandwidth to Nvidia’s B300 family of chips launched last year, but only about half the FP8 and a third the FP4 compute.
While a big step up for the Chinese chip designer, it still has a long way to go to catch up with Nvidia’s Rubin and AMD's recently launched MI455X which promise higher compute and bandwidth. Rubin boasts between 35 and 50 petaFLOPS of FP4 performance, 288 GB of HBM4 memory, and 22 TB/s of bandwidth, putting it in a different league.
Having said that, neither of those chips is available for sale in the Middle Kingdom, so it's not like Chinese model devs have better options.
For its upcoming 960-series accelerators, Huawei is going a similar route using near packaged optics to scale its compute domain to as many as 4,096 chips capable of delivering up to 16 exaFLOPS of FP4 compute.
Huawei says NPO allowed it to consolidate 48,000 800 Gbps optical pluggables into 5,500 of its Hi-One NPO units, cutting power consumption by 550 kilowatts and failure rates in half.