Use of fixed-point divide in video encode stream control

Abstract

A method for applying division of solving fixed-point number in video code flow rate control uses fixed-point processor to realize fixed-point division by utilizing NEWTON-RAPHSON iteration algorithm of Xi +1=Xi ( 2-DXi ). The method can raise operation speed of division in calculation course maximally under condition that minimum accurate requirement of video compression flow rate control is satisfied.

Description

technical field [0001] The invention relates to the fixed-point calculation technology of the micro-processing chip, especially the application of the technology in video coding flow control. Background technique [0002] The principle of division adopted by current fixed-point processor chips is a process in which the divisor is gradually shifted and compared with the dividend. Subtraction is performed at each step, and if it can be subtracted, a bit is inserted into the quotient. However, the calculation overhead of such an algorithm is relatively large, and the number of clock cycles (CYCLE) required can reach hundreds. In applications that require higher computing speed than precision, such as video encoding flow control, such a large number of CYCLEs will obviously increase CPU load and system power consumption. [0003] Ordinary Newton (NEWTON-RAPHSON) iteration method provides a method of multiplying, adding or shifting in floating-point operations to realize divisio...

AI Technical Summary

Problems solved by technology

[0009] b. It does not specify how to set the initial value of the iteration, and the setting of the initial value has a great influence on the accuracy of the final calculation result and the number of operating clock cycles required

[0010] c. It cannot be directly used in the calculation of fixed-point reciprocal or division, especially it does not consider how to prevent overflow in the calculation process

Images