Advanced Micro Devices had 35 patents in artificial intelligence during Q4 2023. AMD’s patents in Q4 2023 focus on techniques for smart feedback design in verification, training data in a computer system, emulating compute kernels with artificial neural networks (ANN), activation scaled clipping layers for neural networks, and hardware acceleration of machine learning designs. These innovations aim to improve efficiency, accuracy, and performance in various aspects of circuit design, data processing, and machine learning implementation. GlobalData’s report on Advanced Micro Devices gives a 360-degreee 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.
Advanced Micro Devices grant share with artificial intelligence as a theme is 51% in Q4 2023. Grant share is based on the ratio of number of grants to total number of patents.
Recent Patents
Application: Smart feedback design for verification (Patent ID: US20230419006A1)
The patent filed by Advanced Micro Devices Inc. describes techniques for implementing a smart feedback design for verification that can reduce production and verification time by allowing selective, accurate, and exhaustive verification of components of a circuit design before the final design is completed. This involves providing smart feedback to circuit nodes in an emulation model based on signals detected at the nodes, enabling simulation of behavior for unavailable or unverified components. The smart feedback allows verification of the emulation model without waiting for all components to be provided or verified, and a request for manufacture can be generated based on aspects of the emulation model to verify a fabricated circuit similarly.
The method outlined in the patent involves receiving a circuit representation with a node and associated feedback representation, simulating circuit operation, and providing simulated feedback at the node based on the simulated circuit output. The feedback can be configured to control the simulated feedback, including simulating virtualized components, producing errors or distortions, and can be based on behavioral or machine learning models. The patent also includes instructions for manipulating processors to perform these actions, as well as an emulation model with a circuit representation and feedback representation to provide feedback based on signals generated by the circuit at the node.
To know more about GlobalData’s detailed insights on Advanced Micro Devices, 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.
