期刊名称：TELKOMNIKA (Telecommunication Computing Electronics and Control)
印刷版ISSN：2302-9293
出版年度：2015
卷号：13
期号：4
页码：1145-1152
DOI：10.12928/telkomnika.v13i4.1894
语种：English
出版社：Universitas Ahmad Dahlan
摘要：Square root is one of the mathematical operations which are widely used in digital signal processing. Its implementation on hardware such as FPGA will provide several advantages compare to the performance offered in software. There are several algorithms which can be utilized for this calculation, but they are difficult to be implemented in FPGA. This paper presents a model of FPGA based square root calculator, which requires very low resources usage, thus occupying very low area of FPGA. The model is designed to suit the needs of medium-speed and low-speed applications which don’t need very high processing speed, while optimizing the number of resources utilized.The modified non-restoring algorithm is used in this design to compute the square root. The design is coded in RTL VHDL, and implemented in Altera DE2-board for hardware validation. The implementation produced very precise square root calculation, with low latency computation and low area consumption, for various input data width tested.
其他摘要：Square root is one of the mathematical operations which are widely used in digital signal processing. Its implementation on hardware such as FPGA will provide several advantages compare to the performance offered in software. There are several algorithms which can be utilized for this calculation, but they are difficult to be implemented in FPGA. This paper presents a model of FPGA based square root calculator, which requires very low resources usage, thus occupying very low area of FPGA. The model is designed to suit the needs of medium-speed and low-speed applications which don’t need very high processing speed, while optimizing the number of resources utilized.The modified non-restoring algorithm is used in this design to compute the square root. The design is coded in RTL VHDL, and implemented in Altera DE2-board for hardware validation. The implementation produced very precise square root calculation, with low latency computation and low area consumption, for various input data width tested.
