SC Build : a computer-aided design tool for design space exploration of embedded central processing unit cores for field-programmable gate arrays

• Published in: IET computers & digital techniques Vol. 3; no. 1; pp. 24 - 32
• Main Authors: ANDERSON, I. D. L, KHALID, M. A. S
• Format: Journal Article
• Language: English
• Published: Stevenage Institution of Engineering and Technology 2009; John Wiley & Sons, Inc
• Subjects: Applied sciences; Circuit properties; Computer aided design; Design. Technologies. Operation analysis. Testing; Digital circuits; Electric, optical and optoelectronic circuits; Electronic circuits; Electronics; Exact sciences and technology; Gate arrays; Genetic algorithms; Hardness; Integrated circuits; Integrated circuits by function (including memories and processors); Mathematical models; Microprocessors; Semiconductor electronics. Microelectronics. Optoelectronics. Solid state devices; Space exploration; Hardware description languages; Processor; Circuit design; Genetic algorithm; s parameter; Evolutionary algorithm; Integrated circuit; Critical path; Field programmable gate array; Delay time; Computer aided design
• ISSN: 1751-8601; 1751-861X
• DOI: 10.1049/iet-cdt:20070120

A genetic algorithm-based design space exploration technique using parameterised cores is examined. A computer-aided design tool called SCBuild was developed which is capable of applying a genetic algorithm to a core's parameters, and generating hardware description language models of core variants. The tool can also compute estimates of a variant's area and critical path delay on a field-programmable gate array. Using this tool, several experiments were conducted using a soft-core processor with a large design space. It was concluded from these experiments that using a genetic algorithm to explore the design space of a parameterised core can help a designer make intelligent decisions regarding the assignment of values to the parameters of an embedded hardware platform.