Quickly design LSI that demonstrates performance by leveraging the characteristics of the processing.
Information and Communication Technology (Saitama University Research Seed Collection 2025-27 p.77)
Keywords: High-performance LSI design, design automation, low power consumption
LSI (Large Scale Integration) refers to digital circuits created by combining nanoscale circuit elements (transistors) on semiconductor wafers approximately 1mm to 10mm in size, with some large-scale devices exceeding 100 million elements. They are embedded in various information communication devices, home appliances, and automobiles, handling signal processing, image processing, numerical calculations, control, and storage. Compact and low-power LSI is an essential technology for realizing IoT. LSI enhances processing performance through parallel processing utilizing a large number of elements. By identifying the characteristics of the processing to be executed by the LSI, we devise processing methods that can be executed quickly and with low power consumption, proposing excellent designs that allow the LSI to achieve optimal performance. Additionally, to obtain the desired LSI more quickly, we automate the LSI design process. Considering the parallelism of numerous calculations involved during processing, we explore combinations of execution order and allocation using computers, developing automated designs for the best LSI in terms of area, speed, and power consumption in a short time.
Inquire About This Product
basic information
Kazuhito Ito, Professor Graduate School of Science and Technology, Department of Mathematical and Electronic Information, Field of Electrical and Electronic Physics 【Recent Research Themes】 ● Development of design automation methods for register-bridge type parallel architectures suitable for LSI ● Proposal of circuit methods for high-reliability LSI through redundancy and development of design automation methods ● LSI design that balances static power consumption reduction and delay time increase suppression ● Design of LSI that executes Ising model annealing quickly and efficiently ● Design of LSI that performs inference in machine learning quickly and efficiently
Price range
Delivery Time
Applications/Examples of results
【Appeal Points to the Industry】 ● Analysis of the characteristics of the processing to be implemented in LSI and design of high-performance LSI leveraging those characteristics ● Parallel acceleration for LSI implementation of still image, video processing, and deep inference ● Fast automatic exploration of multiple LSI implementation options using computers ● Automation of LSI design through versatile operation scheduling exploration combining simulated annealing and integer programming 【Examples of Practical Use, Applications, and Utilization】 ● Development of design automation methods to minimize power consumption of data communication within LSI ● LSI design based on architecture aimed at reducing data communication to accelerate processing speed ● Development of processors and accelerators to speed up error correction coding/decoding processes ● Dual redundancy circuit configuration to detect and correct errors in circuits controlling computational processes within LSI ● Proposal of SIFT image feature point detection method for LSI and its implementation in LSI
Detailed information
-
Verification of real-time SIFT feature point detection LSI operation
catalog（1）
Download All Catalogs
Company information
The Saitama University Open Innovation Center is a center that functions as a liaison office for industry-academia-government collaboration. It consists of three departments: the Industry-Academia-Government Collaboration Department, the Intellectual Property Department, and the Startup Support Department, each staffed with coordinators well-versed in various fields. The center's activities include solving technical challenges in companies, supporting the implementation of joint research, and conducting technology transfer aimed at introducing and utilizing Saitama University's intellectual property.