Cloud Matrix 384
Huawei's large-scale AI processing system architecture consisting of 384 Ascend chips connected across 12 racks using optical interconnects, designed for training large-scale AI models.
As defined in The Geopolitics of AI Infrastructure - Dylan Patel, SemiAnalysis
Where it comes up · 1
Most important claims · 2 of 2Search all claims for “Cloud Matrix 384” →
- Huawei's Ascend 910B and C chips, packaged into the Cloud Matrix 384 system with 384 chips connected across 12 racks using optics and power distribution, represent an architecture that Nvidia attempted with the DGX H100 Ranger (256 GPUs) but failed to bring to production due to cost, power consumption, and reliability issues.The Geopolitics of AI Infrastructure - Dylan Patel, SemiAnalysis
- Huawei's Ascend 910B and C chips, integrated into the Cloud Matrix 384 system architecture with 384 chips connected across 12 racks using optics and power infrastructure, represents an architecture that Nvidia attempted and failed to deploy called DGX H100 Ranger, which had 256 Nvidia GPUs connected in NVLink but proved too expensive, power-hungry, and unreliable to bring to production.The Geopolitics of AI Infrastructure - Dylan Patel, SemiAnalysis