浮点正余弦函数的FPGA及自定义指令实现

The implementation of Custom instruction of floating sin&cos function based on the FPGA

介绍了CORDIC算法的基本原理,并且对CORDIC内核、前处理和后处理单元进行了讨论。通过增加迭代次数,对参数进行了优化筛选,提高了运算精度,使设计出的超越函数能够在精度要求较高的场合中运行。输出数据经过IEEE-754标准化处理,能够直接兼容大多数处理器,扩展了其应用范围。最后通过增加自定义指令的方式完成了部分超越函数的软硬件测试及其对比。

This paper introduces the basic principles of the CORDIC algorithm, it makes some research about CORDIC kernel, pre- processor unit and post- processor unit. It improves the calculation precision through increasing the iteration times, optimizing and selecting the arguments based on the traditional CORDIC algorithm, making the designed soft-core adapted to higher precision required occasion. The output data can be directly compatible with most of the processors by the IEEE-754 standard processing, so its application area is widely extended. Finally it accomplish the soft and hardware tests and compares of some trigonometric functions by adding custom instruction on the Nios II.