Recently, Fast Technology was informed that Alibaba Dharma is developing a neural network chip called Ali-NPU. The chip will be used in image-based video analysis, machine learning and other AI reasoning calculations. According to the design, the chip's cost performance will be 40 times that of current products..
It is understood that the research and development of this chip will better realize the application of AI intelligence in commercial scenarios in the future, which will increase the calculation efficiency and reduce the cost.
Ari Dharma researcher arrogantly introduced, CPU, GPU as a general-purpose computing chip, designed to deal with thread logic and graphics, high power consumption when dealing with AI calculation problems, low cost, in the field of AI computing need dedicated architecture chip to solve the above problems.
At present, Alibaba’s independently developed AI chip, Mainly to solve the image, video recognition, cloud computing and other business scenarios of AI reasoning and computing problems, improve computing efficiency and reduce costs.
According to the pride, Ali-NPU's own research and development of Ali-NPU, based on the advantages of a large number of algorithm models accumulated in the AI field by Alibaba's machine intelligence technology labs, design of micro-structures and instruction sets based on the AI algorithm model, and achieving the maximum amount at the minimum cost AI model algorithm operation.
According to the design, Alibaba's Ali-NPU performance will be 10 times that of mainstream CPUs and GPU architecture AI chips currently on the market, while its manufacturing cost and power consumption are only half, and its cost-effectiveness is more than 40 times. In the future, Ali-NPU's capabilities can not only be more Good to meet the video, image processing needs, can also be output through Alibaba Cloud computing capabilities, empower all walks of life.
In fact, Alibaba has a long-term layout of talents for self-developed AI chips.
'Self-developed AI chip' has become a strategic part of Alibaba's layout of 'China Core'. At present, the R&D team of the Boomerang has reached dozens of people in the United States and Shanghai, and it is expected to reach 100 at the end of the year. Prior to this, Ali had invested Cambrian, Barefoot Networks, Shen Jian, Kneron, ASR, Zhongtian Micro and many other chip companies.
Analysis of the industry, the move for domestic companies independent research and development of core technology, has a great lead effect.
Recently, the U.S. Department of Commerce announced that it will ban the sale of any electronic technology or telecommunications components to Chinese telecommunications equipment manufacturer ZTE for the next seven years.
This incident not only affected high-tech companies including ZTE, but also caused a profound topic in the public opinion field. The export embargo hit the pain point of the lack of core technologies in the Chinese communications industry. Sternly before people.
On the other hand, Chinese companies are investing heavily in scientific and technological research and development.
