Trigonometric function operation circuit based on fixed point number

Abstract

The invention discloses a trigonometric function operation circuit based on a fixed point number. According to the trigonometric function operation circuit, a preprocessing module (101) is connected with a DDR module (100); an iterative operation module (103) is connected with the preprocessing module (101); under the driving of a counting beat number of an iterative counting module (102), according to an operation result symbol bit determined in advance by preprocessing results of an operand I and an operand II output by the pre-processing module (101), an input operand serves as the next input of a current stage at current output of the current stage to form a feedback structure for iteration in the same stage; and after 16-time iterative operation is completed, a trigonometric functionresult of complement processing is output. Compared with the prior art, the operation circuit disclosed by the invention saves software instruction resources of a processor, and ensures the operationprecision not to be changed on the premise that the circuit scale is unchanged.

Description

technical field [0001] The invention relates to the field of integrated circuits, relates to a trigonometric function calculator, in particular to a trigonometric function calculation circuit based on fixed-point numbers. Background technique [0002] In computer software instructions, when it comes to the calculation of trigonometric functions, the software often needs to call a special trigonometric function library, and then run dozens or hundreds of instructions to complete the calculation of a trigonometric function, which is extremely inefficient. Moreover, as the accuracy of the function increases, the computational complexity also increases geometrically. Therefore, the instruction of the trigonometric function is often the most time-consuming part of the software instruction. However, the method of using hardware circuits to complete the calculation of trigonometric functions has a great advantage in saving software instructions, and does not need to consume too ma...

AI Technical Summary

Problems solved by technology

Although this structure greatly improves the computing speed of the system, the scale of the circuit is large, and the accuracy of the computing results is limited by the number of pipeline stages. To improve the computing accuracy, the pipeline stages must be increased, which further increases the hardware overhead.

Images