<p>➀ Huawei has unveiled the CloudMatrix 384, an AI accelerator and rack-scale architecture that competes with Nvidia's GB200 NVL72.</p><p>➁ The system uses 384 Ascend 910C chips, achieving impressive performance despite each chip being only one-third the performance of an Nvidia Blackwell GPU.</p><p>➂ The CloudMatrix 384 offers 300 PFLOPs of dense BF16 compute, almost double that of the GB200 NVL72, with over 3.6x aggregate memory capacity and 2.1x more memory bandwidth.</p>
Related Articles
- Nvidia warns U.S. AI hardware export rules could backfire, empowering Huawei to define global standards5 months ago
- Nvidia's CEO says China is not far behind the U.S. in AI capabilities5 months ago
- Danger On The Digital Silk Road Warns Nvidia6 months ago
- DeepSeek research suggests Huawei's Ascend 910C delivers 60% Nvidia H100 inference performance8 months ago
- Chinese company announces trial production of HBM2, while HBM3E is here, and HBM4 is close9 months ago
- Huawei sticks to 7nm for latest processor as China's chip advancements stall10 months ago
- TikTok owner ByteDance to train its AI model using 100,000+ of Huawei's new Ascend AI chipsabout 1 year ago
- Fujitsu and Nvidia hook up on AI agents8 days ago
- AI bubble conundrum8 days ago
- Nvidia's new CPX GPU aims to change the game in AI inference — how the debut of cheaper and cooler GDDR7 memory could redefine AI inference infrastructure13 days ago