usatoday24
Nvidia’s greatest strength is not her hardware; it is CUDA (Compute Unified Device Architecture). And is that most of the projects of artificial intelligence (AI) that are currently being developed are implemented on this tool. This technology brings together the compiler and development profits used by programmers to develop their software for NVIDIA GPUs, and replace it with another option in the projects that are already underway it is a problem.
Huawei, who aspires to an important portion From this market in China, it has Cann (Compute Architecture for Neural Networks), which is its alternative to CUDA, but at the moment this last software dominates the market. And at the current situation it is a problem for the Chinese companies they want, as proposed by the Government led by Xi Jinping, stop using US hardware and software. For China to have an effective alternative to CUDA is crucial right now, and it seems that it is already ready.
Moore Threads is China’s Nvidia
Li Guojie, a computer scientist from the Chinese Academy of Sciences that is considered an authority in China, holds that the most advanced Chinese GPUs, such as chips Ascend 910 from HuaweiThey are comparable to the current NVIDIA solutions in terms of calculation capacity. However, this expert also defends that in the current circumstances for this Asian country it is crucial to break down all the barriers imposed by CUDA.
“China must develop an alternative system to achieve self -sufficiency in AI (…) Deepseek has had an impact on the Cud that exceed Cuda“, Guojie says. Perhaps Cann manages to break down little by little and manages to impose himself finally, but while he persists to some extent the development of AI in China will continue to depend on the US.
“We need to establish a set of software tool systems for controllable that exceed CUDA”
However, Cann is not the only trick of the country governed by Xi Jinping. Moore Threads It is one of the Chinese companies that are dedicated to the production of hardware for which companies aligned with the interests of the US and its allies cannot sell software or advanced equipment. Although it is very young (it was founded in 2020) it has something very important in its favor: its founder is Zhang Jianzhong, former general manager of the Nvidia subsidiary in China, so it is evident that he knows well what he has in hand.
Moore Threads has developed several GPU for AI applications that, on paper, rival some of the advanced solutions that have placed in the Nvidia, AMD or Huawei market. The cards MTT S4000 and MTT S3000 They are its most interesting proposals right now, although, curiously, in its porpholio the MTT S80 card also appears, a proposal for games and content creation that, according to Moore Threads itself, has a calculation capacity of 14.4 Tflops in single -precision floating coma operations. It doesn’t impress, but it’s not bad at all.
However, this company has something else: a software package with which the domain of CUDA seeks to break. He calls it MUSEis compatible with the range of MTT cards that I have mentioned a few lines above and incorporates a compiler, execution libraries, specialized libraries and code purification tools. However, this is not all.
On paper its most attractive capacity for China is that it allows Reuse the code written in CUDAmoving it so that it can be executed About Moore Threads’ cards. It is difficult to predict what reception the hardware and software of this company will have in your country of origin, but there is no doubt that it is worth following the track.
Image | Moore Threads
More information | Moore Threads
GIPHY App Key not set. Please check settings