China Pacific Insurance (Group) has been granted a patent for a method to reduce power consumption in machine learning hardware accelerators. By optimizing in-flight operations and eliminating unnecessary memory access, the system increases computational throughput and reduces overall power consumption significantly. GlobalData’s report on China Pacific Insurance (Group) gives a 360-degree view of the company including its patenting strategy. Buy the report here.
Smarter leaders trust GlobalData
According to GlobalData’s company profile on China Pacific Insurance (Group), Digital lending was a key innovation area identified from patents. China Pacific Insurance (Group)'s grant share as of May 2024 was 52%. Grant share is based on the ratio of number of grants to total number of patents.
Method for reducing power consumption in machine learning hardware
A recently granted patent (Publication Number: US12001262B2) discloses a method and system for reducing power consumption in machine learning hardware accelerators. The method involves retrieving input data from a source memory, using a compute cache to perform arithmetic operations on the input data, and transferring the result to a hardware accelerator for convolution operations without generating intermediate data. This process helps in reducing read and write operations, ultimately leading to power savings. The hardware accelerator is a separate circuit from the compute cache, ensuring efficient processing without unnecessary data handling.
The system described in the patent includes a source memory for storing input data, a compute cache connected to the source memory to perform arithmetic operations, and a hardware accelerator linked to the compute cache and a data memory. The hardware accelerator executes convolution operations and generates outputs without the need for intermediate data storage or retrieval, thereby reducing read and write operations. The compute cache can be integrated into the source memory or the hardware accelerator and can be implemented in various forms such as a read access memory cell structure, a register-based hardware structure, or a logic circuit. By optimizing the processing of input data and reducing the number of layers processed in a neural network, the method and system outlined in the patent aim to enhance the efficiency of machine learning hardware accelerators while minimizing power consumption.
To know more about GlobalData’s detailed insights on China Pacific Insurance (Group), 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.
