Cambricon Technologies had 43 patents in artificial intelligence during Q2 2024. Cambricon Technologies Corp Ltd filed patents for an integrated circuit chip apparatus designed for executing operations of a neural network with low power consumption. The apparatus includes a control module with an instruction caching unit, an instruction processing unit, and a storage queue unit to improve operation efficiency when performing neural network model operations. GlobalData’s report on Cambricon Technologies gives a 360-degree view of the company including its patenting strategy. Buy the report here.
Smarter leaders trust GlobalData
Access deeper industry intelligence
Experience unmatched clarity with a single platform that combines unique data, AI, and human expertise.
Cambricon Technologies had no grants in artificial intelligence as a theme in Q2 2024.
Recent Patents
Application: Integrated circuit chip apparatus (Patent ID: US20240152741A1)
The patent filed by Cambricon Technologies Corp Ltd describes an integrated circuit chip apparatus designed for executing multiplication, convolution, or training operations of a neural network with minimal calculations and low power consumption. The apparatus includes a main processing circuit that converts data between different data types, transfers data and computation instructions to basic processing circuits, and performs neural network computations. The basic processing circuits execute computations in the target data type and transfer results back to the main processing circuit for further processing. The main processing circuit can handle data type conversions, inner product computations, accumulation of results, and sorting based on the computation instruction provided.
Additionally, the integrated circuit chip apparatus can divide data into distribution and broadcasting blocks, convert data types as needed, distribute data to basic processing circuits, and perform operations such as multiplication or convolution based on the computation instruction. The apparatus includes main registers, basic registers, and various processing units like vector computing units, arithmetic and logic units, accumulators, and data type conversion circuits. The method for performing neural network operations using this apparatus involves data type conversion, transferring data and instructions, executing computations in basic processing circuits, and performing additional computations in the main processing circuit. The method also includes handling different data types, partitioning data blocks, and distributing data to basic processing circuits for parallel processing.
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, 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.
