How Huawei’s New AI Chip Aims to Rival Nvidia and AMD GPUs

Huawei is developing a new AI‑focused GPU‑style chip that mirrors Nvidia and AMD architectures, aiming to ease Chinese developers’ shift from Nvidia hardware, but still faces software compatibility hurdles due to reliance on CUDA and ongoing U.S. export restrictions.

Open Source Linux
Open Source Linux
Open Source Linux
How Huawei’s New AI Chip Aims to Rival Nvidia and AMD GPUs

According to foreign tech media The Information 's Friday report, Huawei Technologies Co., Ltd. is developing a new artificial intelligence chip design that will boost its processor performance, enabling it to handle a broader range of AI development tasks.

The report says the new design will be closer to the architectures used by Nvidia and AMD, i.e., a general‑purpose GPU rather than an AI‑specific chip. This similarity should make it easier for Chinese AI developers to transition from Nvidia’s chips to Huawei’s alternative.

Huawei aims to make its chips more attractive to Chinese tech companies. Although U.S. export controls have made acquiring Nvidia processors increasingly difficult, Chinese tech firms still prefer Nvidia’s processors.

While Chinese tech firms have tested Huawei chips, few have fully adopted them. This reluctance largely stems from developers’ long‑term reliance on Nvidia’s CUDA software development tools, creating challenges when adapting to Huawei’s very different software ecosystem.

With the planned new chip design, AI developers using Huawei processors will be able to run code written for Nvidia’s software platform. However, Huawei still needs to develop software that translates Nvidia instructions into a form its own chips can understand.

Source: EETOP

图片
图片
CUDAGPUNVIDIAChip DesignAI chipHuawei
Open Source Linux
Written by

Open Source Linux

Focused on sharing Linux/Unix content, covering fundamentals, system development, network programming, automation/operations, cloud computing, and related professional knowledge.

0 followers
Reader feedback

How this landed with the community

Sign in to like

Rate this article

Was this worth your time?

Sign in to rate
Discussion

0 Comments

Thoughtful readers leave field notes, pushback, and hard-won operational detail here.