Cambricon Technologies has filed a patent for a data processing method involving obtaining and executing content of a descriptor to process tensor data efficiently. The method includes determining data address and executing data processing based on the descriptor. GlobalData’s report on Cambricon Technologies gives a 360-degree view of the company including its patenting strategy. Buy the report here.

Access deeper industry intelligence

Experience unmatched clarity with a single platform that combines unique data, AI, and human expertise.

Find out more

According to GlobalData’s company profile on Cambricon Technologies, User journey analytics was a key innovation area identified from patents. Cambricon Technologies's grant share as of January 2024 was 20%. Grant share is based on the ratio of number of grants to total number of patents.

Data processing method using descriptors for tensor data

Source: United States Patent and Trademark Office (USPTO). Credit: Cambricon Technologies Corp Ltd

A recently filed patent (Publication Number: US20240028334A1) discloses a data processing method and apparatus for efficient tensor data processing. The method involves obtaining the content of a descriptor when an operand of a processing instruction includes the descriptor, which indicates the shape and data address of tensor data. By executing the processing instruction based on the descriptor content, the method determines the data address in a storage space and performs data processing accordingly. The descriptor can represent N-dimensional tensor data, with shape and address parameters guiding the processing.

Furthermore, the patent details the data processing apparatus, including a controller to obtain descriptor content and a processing circuit to execute instructions based on the descriptor. The apparatus efficiently handles data access instructions for source and target data, retrieving descriptor content from storage space and determining data addresses for processing. The method and apparatus are designed for neural network chips, enhancing data processing capabilities for various applications. This patent showcases advancements in data processing techniques, particularly for tensor data, with a focus on optimizing processing efficiency and accuracy in neural network operations.

To know more about GlobalData’s detailed insights on Cambricon Technologies, buy the report here.

Data Insights

From

The gold standard of business intelligence.

Blending expert knowledge with cutting-edge technology, GlobalData’s unrivalled proprietary data will enable you to decode what’s happening in your market. You can make better informed decisions and gain a future-proof advantage over your competitors.

GlobalData

GlobalData, the leading provider of industry intelligence, provided the underlying data, research, and analysis used to produce this article.

GlobalData Patent Analytics tracks bibliographic data, legal events data, point in time patent ownerships, and backward and forward citations from global patenting offices. Textual analysis and official patent classifications are used to group patents into key thematic areas and link them to specific companies across the world’s largest industries.