This inventor holds 5 USPTO granted patents and 1 published patent application. Top assignee: Rebellions Inc.. Active years: 2023-2026.
Company Filing History:
Years Active: 2023-2026
Title: The Innovations of Donghan Kim
Introduction
Donghan Kim is a prominent inventor based in Seongnam, South Korea. He has made significant contributions to the field of neural processing technology. With a total of 5 patents to his name, Kim is recognized for his innovative approaches to enhancing computational efficiency in neural devices.
Latest Patents
One of Kim's latest patents is a neural processing device that comprises a processing unit designed to perform calculations. This device includes an L0 memory that receives data from the processing unit and provides data back to it. Additionally, it features a Load/Store Unit (LSU) that performs load and store operations of the data. The LSU is equipped with a neural core load unit and a neural core store unit, which issue load and store instructions, respectively. A sync ID logic is also included to generate synchronization signals for each sync ID.
Another notable patent is related to a neural processing device and a load/store method for the device. This invention involves a processing unit that receives input activation and weight to perform a two-dimensional matrix calculation. The device includes a first memory and an LSU that manages memory access operations between the first memory and a second memory. The memory access operations are designed to optimize processing efficiency during current and standby operations.
Career Highlights
Donghan Kim is currently employed at Rebellions Inc., where he continues to develop cutting-edge technologies in neural processing. His work has positioned him as a key figure in the advancement of computational devices.
Collaborations
Kim collaborates with talented coworkers, including Jinwook Oh and Jinseok Kim. Their combined expertise fosters an innovative environment that drives the development of new technologies.
Conclusion
Donghan Kim's contributions to neural processing technology exemplify his commitment to innovation. His patents reflect a deep understanding of computational efficiency and the future of neural devices.