Computing power resource configuration method and device

Abstract

The embodiment of the invention discloses a computing power resource configuration method and device which can be applied to the field of automatic driving and can be applied to intelligent automobiles, automatic driving automobiles, connected automobiles and the like, and the method comprises the steps that any domain controller (DCU) of a vehicle receives computing power configuration data corresponding to the DCU and sent by a cloud server or an upper computer, the computing power configuration data comprises the preset configuration number of various types of processors (including processor cores) in the DCU, the DCU resets a target processor in the DCU according to the computing power configuration data, and under the condition that the perception information collected by the vehicle belongs to the processing category of the DCU, the perception information is processed based on the reset target processor. The computing power configuration data supports updating of near-end upgrade (UDS) or far-end upgrade (OTA), the computing power configuration data can be updated according to needs so as to adjust computing power resources in the DCU, the computing power resources are saved on the premise of guaranteeing smooth operation of services, and the situation that the corresponding computing power configuration data can only be solidified in eFuse and cannot be modified when the DCU leaves a factory is avoided.

Description

technical field [0001] The present application relates to the field of autonomous driving, and in particular, to a method and device for configuring computing resources. Background technique [0002] Since the invention of the automobile, after more than 100 years of development, it has become an indispensable part of people's lives. With the improvement of living standards, people have higher and higher requirements for travel comfort and convenience. Evolve in the direction of intelligence. With the advent of autonomous driving, due to the need to achieve multi-sensor access, fusion, perception, positioning, regulation and other functions, the hardware needs to provide a large amount of computing power. One of the original functions corresponds to an electronic control unit (ECU). ) distributed computing architecture has been unable to adapt to the demand, such as GPS, camera, lidar, millimeter-wave radar and wheel speed sensors and other data (also known as perception in...

AI Technical Summary

Problems solved by technology

[0004] The above computing power resource configuration method is to configure all processors (including processor cores) in the DCU. This is because the computing power required for subsequent different automatic driving functions cannot be accurately estimated before the DCU leaves the factory. The programming configuration is performed according to the maximum computing power resource, but in the actual application process of the DCU, such a large computing power resource may not be needed, resulting in a waste of resources; secondly, the computing power configuration data is programmed in the eFuse, and the eFuse As a one-time programmable memory, it cannot be changed later

Images