Division function realization method, circuit, chip and system

Abstract

The application relates to a division function realization method, circuit, chip and system. The method includes: obtaining the variable value of the division function to be processed; inputting the variable value into the second-order function processing model to obtain the second-order function value; inputting the variable value into the second-order nonlinear interpolation function processing model to obtain the second-order nonlinear interpolation function value; obtain the product of the second-order function value and the second-order nonlinear interpolation function value, the product is output as the function value of the division function to be processed, the present invention carries out the initial approximate calculation of the division function to be processed by the second-order function processing model, and then through two The first-order nonlinear interpolation function processing model accurately calculates the division function to be processed. Among them, the second-order function processing model adopts the second-order function, which improves the accuracy of the division function calculation; the coefficients in the second-order nonlinear interpolation function processing model have symmetry nature, which greatly reduces the processor's occupation of hardware resources when performing division function operations.

Description

technical field [0001] The present application relates to the technical field of data processing, in particular to a division function realization method, circuit, chip and system. Background technique [0002] Basic arithmetic operations are the basis of mathematical calculations and the premise for computers to perform complex calculations. The division function is the most basic type of arithmetic operation function. It is widely and important in digital signal processing, image processing, coordinate axis transformation and scientific calculation. Applications. Although the performance of the processor is improved year by year with the progress of the process technology, the operation process of the processor still needs to consume a lot of calculation time when performing the division function operation. For example, a floating-point division may take 20 to 30 computing cycles, much higher than the 4 to 5 computing cycles required by a multiplier. [0003] In the trad...

AI Technical Summary

Problems solved by technology

[0003] In the traditional technology, there are both software method to realize division calculation and hardware circuit to realize division calculation. Among them, the method of realizing division calculation through hardware circuit, such as the division calculation method based on Newton-Raphson division function hardware, but, During the implementation process, the inventors found that the traditional technology has at least the following problems: when ensuring high calculation accuracy, it consumes a lot of hardware resources, resulting in high calculation costs

Images