CN117632830A

CN117632830A - HPC system-based chip, vehicle, data processing method, medium and device

Info

Publication number: CN117632830A
Application number: CN202311594690.3A
Authority: CN
Inventors: 张明飞
Original assignee: Suzhou Changxing Zhijia Automobile Technology Co ltd
Current assignee: Suzhou Changxing Zhijia Automobile Technology Co ltd
Priority date: 2023-11-27
Filing date: 2023-11-27
Publication date: 2024-03-01

Abstract

The present invention relates to the field of vehicles, and in particular, to a chip based on an HPC system, a vehicle, a data processing method, a medium, and a device. An intelligent driving domain system and a cabin domain system are deployed on the chip. The intelligent driving domain system is used for processing the first type of business data and generating first target result data. And the cabin domain system is used for processing the second class of service data and generating second target result data. The intelligent driving domain system is used for writing the first target result data into the dynamic random access memory, the cabin domain system is used for writing the second target result data into the dynamic random access memory, and the intelligent driving domain system and the cabin domain system can read the first target result data and/or the second target result data. The intelligent driving domain system and the cabin domain system in the chip provided by the embodiment of the invention can share the memory so as to realize the data transmission function between the two modules. Compared with the existing ms-level transmission speed through a physical bus, the method has the advantage that the transmission speed is greatly improved. And meanwhile, the quality of signal transmission can be ensured.

Description

HPC system-based chip, vehicle, data processing method, medium and device

Technical Field

The present invention relates to the field of vehicles, and in particular, to a chip based on an HPC system, a vehicle, a data processing method, a medium, and a device.

Background

The cabin driving fusion system platform HPC (High Performance Computing, high-performance computing platform) integrates various functions (such as instruments, control, information entertainment and the like) of an automobile cabin and various functions (ACC, LKA, AEB, NOA and the like) of intelligent driving, fuses the functions onto the same HPC hardware platform, depends on certain hardware and software to realize, and creates a more intelligent, efficient and humanized automobile central computing brain. The cabin fusion system platform HPC integrates logic and data among different systems, achieves the aims of cabin and intelligent driving storage information sharing, interface unification, function complementation and hardware multiplexing, improves the experience of a driver and the safety, the intellectualization and the humanization of the cabin, and reduces the complexity and the overall cost of function development of a host factory.

At present, an intelligent driving domain system and a cabin domain system in a vehicle are respectively deployed in different ECUs (Electronic Control Unit, electronic controller units), wherein the intelligent driving domain system and the cabin domain system are respectively responsible for processing data of a panoramic camera and a forward-looking camera, and the intelligent driving domain system and the cabin domain system are respectively responsible for processing data of a panoramic camera and are in communication connection through a physical bus. Because the two are respectively deployed in respective SoCs (systems-on-a-chips), the computation tasks deployed by the two can only call the intermediate results in the internal memory of the two, and physical isolation exists. The data under the architecture needs to be transmitted through a physical bus, the transmission rate is low, and when the data is communicated with the physical bus, the data is easy to be influenced by electromagnetic interference, so that the signal quality is reduced.

Disclosure of Invention

Aiming at the technical problems, the invention adopts the following technical scheme:

according to one aspect of the present invention, there is provided a chip based on an HPC system,

a dynamic random access memory is arranged in the chip. And an intelligent driving domain system and a cabin domain system are deployed on the chip.

The intelligent driving domain system is used for processing the first type of business data and generating first target result data. And the cabin domain system is used for processing the second class of service data and generating second target result data. The first type of traffic data is not exactly the same as the second type of traffic data.

The intelligent driving domain system is used for writing the first target result data into the dynamic random access memory and reading the first target result data and/or the second target result data.

The cabin domain system is used for writing the second target result data into the dynamic random access memory and reading the first target result data and/or the second target result data.

Further, at least one first processing core and at least one second processing core are arranged in the chip. The first processing core and the second processing core are both in communication connection with the dynamic random access memory.

The first processing core is used for being called by the intelligent driving domain system to finish processing the first type of service data and generate first target result data. And the second processing core is used for being called by the cabin domain system to finish processing the second class of service data and generate the second target result data.

Further, the method further comprises the following steps:

an image signal processor system disposed on the chip. The method is used for preprocessing the first type of initial service data to generate the first type of service data. The preprocessing is used for removing noise data and generating a preset data format.

And preprocessing the second-class initial service data to generate second-class service data.

Further, the method further comprises the following steps:

the capacity expansion memory is in communication connection with the dynamic random access memory in the chip and is used for writing data in the dynamic random access memory into the self memory and writing data in the self memory into the dynamic random access memory.

Further, the method further comprises the following steps:

the sensor abnormality detection system is arranged on the chip and is in communication connection with the image signal processor system. And the system is used for detecting whether the target sensor is abnormal according to the first-class service data and the second-class service data.

Further, the sensor abnormality detection system is configured to:

and carrying out abnormality detection on each preset information acquisition component, and generating sensor abnormality information under the condition that any information acquisition component is abnormal.

Further, the intelligent driving domain system is configured to:

and under the condition that a preset auxiliary driving activating instruction is acquired, executing a corresponding auxiliary driving task, and stopping processing the first type of service data.

And under the condition that a preset auxiliary driving closing instruction is acquired, processing the first service data is started, and the first target result data is written into the dynamic random access memory.

Further, the cabin domain system is configured to:

and under the condition that the intelligent driving domain system acquires a preset auxiliary driving closing instruction, processing the second class of service data, and writing second target result data into the dynamic random access memory.

Further, the method further comprises the following steps:

the data sharing system is deployed on the chip and calls the first processing core to read the first target result data and the second target result data stored in the dynamic random access memory and send the first target result data and the second target result data to the target position.

Further, the data sharing system is configured to:

under the condition that the intelligent driving domain system acquires a preset auxiliary driving activating instruction, the data sharing system stops sending the first target result data and the second target result data in the dynamic random access memory to the target address.

Under the condition that the intelligent driving domain system acquires a preset auxiliary driving closing instruction, the data sharing system starts to send first target result data and second target result data in the dynamic random access memory to the target address.

Further, the method is applied to a data processing system of the vehicle. The first type of service data at least comprises image data of a surrounding camera and a front camera of the vehicle, and the second type of service data at least comprises image data of a surrounding camera of the vehicle.

As a second aspect of the present invention, there is also provided a vehicle comprising a chip based on the HPC system as described above.

As a third aspect of the present invention, there is also provided a data processing method based on an HPC system, applied to a first processing chip, in which a dynamic random access memory is provided. And an intelligent driving domain system and a cabin domain system are deployed on the first processing chip.

The data processing method comprises the following steps:

and controlling the intelligent driving domain system to process the first type of service data to generate first target result data.

And controlling the cabin domain system to process the second class of service data to generate second target result data. The first type of traffic data is not exactly the same as the second type of traffic data.

And controlling the intelligent driving domain system to write the first target result data into the dynamic random access memory, and reading the first target result data and/or the second target result data.

And controlling the cabin domain system to write the second target result data into the dynamic random access memory and read the first target result data and/or the second target result data.

As a fourth aspect of the present invention, there is also provided a non-transitory computer readable storage medium storing a computer program which, when executed by a processor, implements a data processing method based on an HPC system as described above.

As a fifth aspect of the present invention, there is also provided an electronic device comprising a memory, a processor and a computer program stored in the memory and executable on the processor, the processor implementing a data processing method based on an HPC system as described above when executing the computer program.

The invention has at least the following beneficial effects:

according to the intelligent driving domain system and the cabin domain system, the intelligent driving domain system and the cabin domain system are both deployed in the same chip, and the computing resources of the corresponding number of processing cores are distributed to the intelligent driving domain system and the cabin domain system so as to realize the corresponding computing tasks, so that the integration level can be improved. Meanwhile, the intelligent driving domain system and the cabin domain system are both in communication connection with the dynamic random access memory in the chip, so that the data in the intelligent driving domain system and the cabin domain system can be read and written. Therefore, the intelligent driving domain system and the cabin domain system can share the memory, and the data transmission function between the two corresponding modules can be realized by reading the data written by the other party in the dynamic random access memory. The data transmission mode is an on-chip communication mode.

Compared with the existing ms-level transmission speed through a physical bus, the transmission speed of the method for on-chip communication can reach ns-level, and the method has great improvement. Meanwhile, the on-chip communication mode has no influence of electromagnetic interference on signals in the physical bus communication mode, and the transmitted signals can be verified by a self-contained signal verification and correction method so as to ensure the quality of signal transmission.

Drawings

In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the drawings required for the description of the embodiments will be briefly described below, and it is apparent that the drawings in the following description are only some embodiments of the present invention, and other drawings may be obtained according to these drawings without inventive effort for a person skilled in the art.

FIG. 1 is a schematic diagram of a chip based on an HPC system according to an embodiment of the invention;

FIG. 2 is a schematic diagram of a chip based on an HPC system according to an embodiment of the invention;

fig. 3 is an interaction schematic diagram of a chip based on an HPC system and a road-end MEC and other target vehicles according to an embodiment of the present invention;

fig. 4 is a schematic diagram of actions provided in the embodiment of the present invention when a preset auxiliary driving activation instruction is obtained by an intelligent driving domain system;

Fig. 5 is a schematic diagram of actions provided in the embodiment of the present invention when a preset auxiliary driving closing instruction is obtained by an intelligent driving domain system;

FIG. 6 is a block flow diagram of a data processing method based on an HPC system according to an embodiment of the invention.

Detailed Description

The following description of the embodiments of the present invention will be made clearly and completely with reference to the accompanying drawings, in which it is apparent that the embodiments described are only some embodiments of the present invention, but not all embodiments. All other embodiments, which can be made by those skilled in the art based on the embodiments of the invention without making any inventive effort, are intended to fall within the scope of the invention.

As a possible embodiment of the present invention, as shown in fig. 1, there is provided a chip based on an HPC system, in which a dynamic random access memory is provided. And an intelligent driving domain system and a cabin domain system are deployed on the chip.

The chip in this embodiment may be an SoC chip, where the chip includes the following parts: a neural network processor (NSP, neural Network signal processor) or a neural network processing Unit (NPU, neuralNetworks Process Units), a vision processor (CVP, computer Vision Processors), an image processing Unit (GPU, graphic Processing Unit), a logic operation processor (CPU, centralProcessing Unit) or an image signal processing Unit (ISP, image Signal Processor) to power the system and the memory.

Preferably, the intelligent driving domain system is deployed with a QNX or Linux system, and the cabin domain system is deployed with an Android system. The Android system is an open operating system, has more open interfaces, is convenient for access of richer applications, but has lower safety performance, so that the Android system is used in a cabin domain system. The QNX or Linux system has higher safety performance, and can ensure the safety of intelligent driving, so that the QNX or Linux system is used in an intelligent driving domain system.

The intelligent driving domain system is mainly responsible for intelligent driving functions, and the functions of the intelligent driving domain system cover the aspects of environment perception (such as obtaining surrounding environment information through radar, laser radar (LiDAR), cameras and other equipment), decision planning (such as determining a driving route and a driving strategy of a vehicle through an algorithm), control execution (such as realizing automatic driving through controlling steering, acceleration, deceleration and the like of an automobile) and the like.

The cabin area system is mainly responsible for comfort, convenience and entertainment inside the car. Including but not limited to control of the environment within the vehicle (e.g., air conditioning, seat conditioning, etc.), infotainment systems (e.g., audio, navigation, connectivity services, etc.), vehicle communications (e.g., internet of vehicles, vehicle-to-vehicle (V2V) communications, vehicle-to-infrastructure (V2I) communications, etc.), driver status monitoring (e.g., fatigue driving warnings), etc. Therefore, in this embodiment, the first type of service data and the second type of service data may be corresponding data in any one or more of the above services, and the corresponding first target result data and second target result data may be data obtained by corresponding processing the first type of service data and the second type of service data. For example, the point cloud data obtained by the laser radar is taken as an example, the directly obtained point cloud data is the first kind of service data, and the data after noise removal and/or target marking is the first target result data.

In a specific embodiment, the intelligent driving domain system is configured to write the first target result data into the dynamic random access memory and read the first target result data.

In a specific embodiment, the intelligent driving domain system is configured to write the first target result data into the dynamic random access memory and read the second target result data.

In a specific embodiment, the intelligent driving domain system is configured to write the first target result data into the dynamic random access memory, and read the first target result data and the second target result data.

In a specific embodiment, the cockpit area system is used for writing the second target result data into the dynamic random access memory and reading the first target result data.

In a specific embodiment, the cabin domain system is configured to write second target result data to the dynamic random access memory and to read the second target result data.

In a specific embodiment, the cabin domain system is configured to write the second target result data to the dynamic random access memory and to read the first target result data and the second target result data.

The chip is provided with a Dynamic Random Access Memory (DRAM), and the intelligent driving domain system and the cabin domain system are both in communication connection with the dynamic random access memory so as to perform read-write operation on the dynamic random access memory. The first processing core is called by the intelligent driving domain system to write the first target result data into the dynamic random access memory, and the second processing core is called by the cabin domain system to write the second target result data into the dynamic random access memory. The first processing core and the second processing core are core chips in the middle of the CPU, are made of monocrystalline silicon, are used for completing all calculation, receiving/storing commands, processing data and the like, and are digital processing cores.

The SoC chip is provided with a high-speed memory DRAM, so that the read-write speed is faster, and the SoC chip is similar to a cache. In this embodiment, the intelligent driving domain system and the cabin domain system are deployed in the same SoC chip, are partitioned and isolated by a virtualization technology, and are all in communication connection with the dynamic random access memory. Therefore, the intelligent driving domain system and the cabin domain system can perform read-write operation on the data (the first target result data and the second target result data) in the intelligent driving domain system and the cabin domain system. The computing tasks deployed by both can share intermediate results in memory. Therefore, the intelligent driving domain system and the cabin domain system can share the memory, and the data transmission function between the two corresponding modules can be realized by reading the data written by the other party in the dynamic random access memory. The data transmission mode is an on-chip communication mode.

Fig. 2 is a schematic structural diagram of a chip based on an HPC system according to an embodiment of the present invention, please refer to fig. 2, wherein the first type of service data may be: front view image information of the vehicle body, peripheral view image information of the vehicle body, point cloud information acquired by a millimeter wave radar, and vehicle body position information acquired by a GNSS (Global Navigation Satellite System ).

In this embodiment, the point cloud information acquired by the millimeter wave radar is directly transmitted to the intelligent driving domain system through the CANFD bus. The vehicle body position information acquired by the GNSS (Global Navigation Satellite System ) can be transmitted to the intelligent driving domain system through a UART (Universal Asynchronous Receiver-Transmitter, universal asynchronous receiver Transmitter) serial port. The point cloud information and the vehicle body position information can be used for related functions of auxiliary driving.

In order to improve the driving assisting capability of some vehicles, various types of image acquisition sensor assemblies and millimeter wave radars are arranged to acquire first-class business data.

Such as: a front vision camera on the vehicle may be used to capture front view image data of the vehicle body. The visual angle is smaller, and a camera module with the angle of 60 degrees is generally adopted to be installed in the middle of a front windshield of a vehicle and is mainly used for sensing a scene far in front of the vehicle, and the sensing distance is generally within 250 meters.

A wide-angle camera on the vehicle may be used to capture raw body perimeter image data. The angle of view is relatively large, and generally about 6 camera modules of 100 degrees are adopted to be installed around a vehicle for one circle, and are mainly used for sensing 360-degree whole body environment. The wide-angle camera has a certain distortion phenomenon.

Specifically, the intelligent driving domain system can be implemented by using existing software for controlling related functions of the intelligent driving domain. The intelligent driving domain system processes the first kind of business data, and mainly marks attributes of targets (such as targets of pedestrians, vehicles, roads, trees and the like) existing in front view image information, peripheral view image information and point cloud information of a vehicle body. Attribute information such as ID, name, or category of the tag target.

Referring to fig. 2, the second type of service data may be: the plurality of sub-looking-around image information of the vehicle body.

Specifically, the plurality of sub-looking-around image information may be collected by a looking-around fisheye camera on the vehicle body. The view angle of the looking-around fisheye camera is larger, can reach more than 180 degrees, has better perception on a short distance, is generally used for parking scenes such as APA (Auto Parkig Assist, automatic parking assist system), AVP (automatic valet parking), and the like, and is arranged at 4 positions below a left rearview mirror, a right rearview mirror, a front license plate, a rear license plate, and the like of a vehicle, so that a plurality of sub looking-around image information can be obtained.

The cockpit area system can also be realized by using the existing related software, and the main function of the cockpit area system is to cut, splice and render the acquired sub-looking-around image information so as to generate a finished looking-around image.

The intelligent driving domain system and the cabin domain system can store the processed data to be shared (namely the first target result data and the second target result data) into the dynamic random access memory, and meanwhile, the intelligent driving domain system and the cabin domain system can realize the data transmission function between the two corresponding modules by reading the data written by the other party in the dynamic random access memory. The data transmission mode is an on-chip communication mode.

At least one first processing core and at least one second processing core are arranged in the chip; the first processing core and the second processing core are both in communication connection with the dynamic random access memory;

The first processing core is used for being called by the intelligent driving domain system to finish processing the first type of service data and generate first target result data; the second processing core is used for being called by the cabin domain system to finish processing the second class of service data and generate second target result data.

Specifically, the following example is given as an illustration, and there are 8 compute cores in the SoC chip. The computing resources of the 8 computing cores can be respectively distributed to the intelligent driving domain system and the cabin domain system according to the quantity of the resources occupied by the computing tasks respectively processed by the intelligent driving domain system and the cabin domain system in actual use. For example, 5 of them (first processing core) may be allocated to the intelligent driving domain system, and the remaining 3 (second processing core) may be allocated to the cabin domain system. Or 4 of them are allocated to the intelligent driving domain system, 3 are allocated to the cabin domain system, and the remaining 1 are allocated to the other modules. Typically, the number of first processing cores will be greater than the number of second processing cores due to the greater computational resources consumed by the tasks performed in the intelligent drive domain system.

As another embodiment of the present invention, as shown in fig. 3, the system further includes: a data sharing system, an image signal processor system, a capacity expansion memory and a sensor abnormality detection system.

The data sharing system is deployed in the chip, has an association relationship with at least one first processing core, and is used for calling the at least one first processing core so as to read the first target result data and the second target result data stored in the dynamic random access memory and send the first target result data and the second target result data to the target position. The data sharing system is communicatively coupled to the dynamic random access memory.

Because, the data sharing system is mainly used for sharing various vehicle body surrounding information processed by the intelligent driving domain system and the cabin domain system to the cloud. The data sharing system is also communicatively coupled to the dynamic random access memory so that information to be shared therein can be read more quickly. Meanwhile, because certain computing resources are required to be occupied in the data sharing process, and the computing resources allocated in the intelligent driving domain system are relatively more sufficient, the data sharing system is generally integrated in the intelligent driving domain system, and at least one first processing core is used for completing corresponding computing tasks.

In addition, the data sharing system can monitor the computing resource occupancy rate of each first processing core in real time after the intelligent driving domain system receives the auxiliary driving activating instruction, and calculate the average resource occupancy rate, and if the average resource occupancy rate is smaller than the preset threshold, the intelligent driving domain system can continue to process the first type of service data while executing the corresponding auxiliary driving task, and share the first type of service data through the data sharing system.

In one embodiment, an image signal processor system is also disposed within the chip. The image signal processor system is respectively in communication connection with the intelligent driving domain system and the cabin domain system. The method is used for preprocessing the initial image information of the surrounding environment of the vehicle to generate first-class service data and second-class service data.

In one embodiment, the image signal processor system may be an ISP module for preprocessing image information of the surroundings of the host vehicle, removing noise data and generating vehicle body environment image information in a preset format. The vehicle body environment image information includes initial vehicle body front view image information, initial vehicle body peripheral view image information, and a plurality of sub-ring view image information.

In one embodiment, the pre-set format of the body environment image information may be RGB or YUV format of the body environment image information.

Specifically, the ISP module is configured to perform the following data preprocessing steps:

the ISP module respectively acquires the original image data acquired by the looking-around camera, the looking-around camera and the looking-ahead camera of the vehicle. Specifically, the around camera, the front camera and the ISP module on the vehicle transmit image information through GMSL (Gigabit Multimedia Serial Links, gigabit multimedia serial link).

And then, the ISP module performs denoising processing on the acquired original image data and generates car body environment image information with a format of RGB or YUV. The versatility of the image data in this format is higher.

The expansion memory is in communication connection with the dynamic random access memory in the chip. The flash Memory may be an existing DDR (Double Data Rate) Memory (i.e., DDR Memory in fig. 1) with a larger capacity (e.g., 1T) to expand the Memory in the system.

In one embodiment, a sensor anomaly detection system is also disposed within the chip. The sensor abnormality detection system is in communication with the image signal processor system. The sensor abnormality detection system is configured to: and carrying out abnormality detection on each preset information acquisition component, and generating sensor abnormality information under the condition that any information acquisition component is abnormal. The information acquisition component includes a target camera. Specifically, the sensor abnormality detection system may determine whether the corresponding camera is normal by detecting whether the image data processed by the image signal processor system meets the requirements. For example, when a large-area obstruction or abnormal image content is detected on an image, the sensor abnormality detection system can generate corresponding alarm information. Similarly, the sensor abnormality detection system also detects abnormality of other sensors in the vehicle, and when any sensor is abnormal, corresponding alarm information is generated.

And when any camera is detected to be abnormal, the data sharing operation is suspended. Because the camera is abnormal, the acquired image information is distorted, the information accuracy is reduced, and data sharing is not performed at this time.

In this embodiment, by setting the data sharing system, the real-time position of the vehicle and the environmental information around the vehicle can be shared to the target address in time. The target address may be set as a road end MEC (Mobile Edge Computing, edge calculation unit) in the intelligent road, for example. Then the road end MEC processes the data and shares the data to be sent to the OBU (On Board Unit) of other target vehicles, so that the road end MEC can obtain more accurate road condition information. In the embodiment, the data sharing system can cooperate with an intelligent road, so that V2X beyond visual range perception is provided while large data sharing is realized, the accident rate on the public road can be reduced to a certain extent, and particularly the long tail problem including cut-in scenes can be better solved.

Meanwhile, software and hardware resources of the intelligent automobile HPC computing brain are fully called in the embodiment, the resource utilization rate is remarkably improved, and innovative application value is provided for the staged transition evolution in the crossover type technical development of the intelligent automobile.

As another embodiment of the present invention, to achieve full utilization of computing resources in the present system, the various modules of the present system are configured as follows.

The intelligent driving domain system is configured to: under the condition that a preset auxiliary driving activating instruction is obtained, the intelligent driving domain system executes a corresponding auxiliary driving task and stops processing the first type of business data.

Under the condition that a preset auxiliary driving closing instruction is acquired, the intelligent driving domain system starts to process the first type of service data and writes the processing result data into the dynamic random access memory.

The preset driving support activation instruction and the closing instruction in this embodiment are opening or closing instructions corresponding to part or all of the functions of the ADAS (Advanced Driving Assistance System, advanced driving support system) in the host vehicle, respectively. The instruction may typically be issued by the driver. Because the part of the ADAS functions are smaller in occupied computing resources after being started, more computing resources remain in the intelligent driving domain system when the functions are started, and the intelligent driving domain system can still be used for processing the first type of business data and sharing the first type of business data to the cloud. So that these small resource occupation function instructions can be avoided when the selection of the preset auxiliary driving instruction is made.

Specifically, when the following functions in the ADAS function are activated during the running of the vehicle, the intelligent driving domain system receives the corresponding activation instruction, and at this time, the intelligent driving domain system stops processing the first type of service data and stops sharing. Such as: APA (automatic parking), RPA (parking for passengers), ALC (automatic lane changing), AES (automatic emergency steering), TJC (traffic jam handling Free), AVP 2.0 (double redundancy for parking for mobile parking places), NOA (high-order navigation assisted driving on expressways and urban roads), ACC (adaptive cruise), LKA (lane keeping assistance) and the like.

When the following functions in the ADAS function are activated, the intelligent driving domain system continues to process the first kind of service data and share the first kind of service data. Such as: AEB (automatic emergency braking), FCW (front collision warning), LDW (lane departure warning), TJA/ICA (traffic jam assist/integrated cruise assist), LAEB (low speed automatic emergency braking), IHC (intelligent headlight control), TSR (traffic sign recognition), BSD (blind zone detection), LCA (lane change assist), DOA (door opening warning), RCTA/B (reverse transverse traffic warning/braking), FCTA/B (forward transverse traffic warning/braking), ELK (emergency lane keeping), DCLC (driver confirmation lane change), DMS (driver fatigue detection), and the like.

The cabin domain system is configured to: and under the condition that the intelligent driving domain system acquires a preset auxiliary driving closing instruction, the cabin domain system processes the second type of service data and writes the processing result data into the dynamic random access memory.

The data sharing system is configured to: under the condition that the intelligent driving domain system acquires a preset auxiliary driving activating instruction, the data sharing system stops sending the processing result data in the dynamic random access memory to the target address.

Under the condition that the intelligent driving domain system acquires a preset auxiliary driving closing instruction, the data sharing system continues to send the processing result data in the dynamic random access memory to the target address.

The sensor abnormality detection system is configured to: the sensor abnormality detection system detects abnormality of each preset information acquisition component, and if any information acquisition component is abnormal, sensor abnormality information is generated.

The image signal processor system is configured to: and respectively acquiring the original image data acquired by the looking-around acquisition assembly, the looking-around acquisition assembly and the looking-ahead acquisition assembly of the vehicle.

Preprocessing the original image data, removing noise data and generating first-type service data and second-type service data in preset formats. The preset format in this embodiment may be: RGB or YUV format, the image information of which has higher versatility.

As shown in fig. 4, in the case that the intelligent driving domain system obtains the preset auxiliary driving activation instruction, the intelligent driving domain system stops processing the first type of service data, and the data sharing system also stops sharing the data to the cloud. At this time, all the computing resources in the intelligent driving domain system can be allocated to the corresponding auxiliary driving functions, so that the corresponding functions can be normally and smoothly performed.

As shown in fig. 5, in the case that the intelligent driving domain system obtains the preset auxiliary driving closing instruction, the computing resources in the intelligent driving domain system are basically in an idle state, so in order to more fully utilize the computing resources, the RTOS (Real Time Operating System, real-time operating system) on the intelligent driving domain system activates the built-in cloud sharing data module by default, that is, the software and hardware resources of the SoC intelligent driving core in the idle state are called, and the intelligent driving domain system can continue to process the first type of service data, and meanwhile, the cabin domain system can also process the second type of service data. The front-end ISP module also synchronously receives and preprocesses the original data of the all-round looking and front-looking cameras to generate image data in a specific format. The intelligent driving domain system and the cabin domain system can store the processed image data into a dynamic random access memory of the SoC chip, then the data sharing system extracts the image data and the radar target ID data stored in the memory block in real time, compresses and packages the data, and shares the data and uploads the data to the road side MEC computing unit. And then the MEC unit converts the received image data of the vehicle and the radar target ID data into a coordinate system through a sensing processing unit of the MEC, and then the coordinate system is issued to other target vehicles by a vehicle cloud sharing module of the MEC so as to use the data.

The chip computing power multiplexing is a method for realizing full utilization of computing power by utilizing idle resources in the chip. The same chip, clock, data bus, memory, etc. may be allocated to different functional modules by dividing and allocating time slots. The scheme in the embodiment adopts a time division multiplexing technology, and is specifically realized based on a mode of distributing time slots, namely: when a driver of the vehicle activates a preset automatic driving function, the system immediately closes the cloud sharing function module and the related function modules in the intelligent driving domain, and timely releases core calculation force, memory resources and the like to the vehicle.

As another embodiment of the present invention, there is also provided a vehicle including the above-described HPC system-based chip.

As another embodiment of the present invention, as shown in fig. 6, there is further provided a data processing method based on an HPC system, which is applied to a first processing chip, and a dynamic random access memory is disposed in the first processing chip. And an intelligent driving domain system and a cabin domain system are deployed on the first processing chip.

The data processing method comprises the following steps:

s100: and controlling the intelligent driving domain system to process the first type of service data to generate first target result data.

S200: and controlling the cabin domain system to process the second class of service data to generate second target result data. The first type of traffic data is not exactly the same as the second type of traffic data.

S300: and controlling the intelligent driving domain system to write the first target result data into the dynamic random access memory, and reading the first target result data and/or the second target result data.

S400: and controlling the cabin domain system to write the second target result data into the dynamic random access memory and read the first target result data and/or the second target result data.

As another embodiment of the present invention, at least one first processing core and at least one second processing core are disposed in a chip. The first processing core and the second processing core are both in communication connection with the dynamic random access memory.

As another embodiment of the present invention, an image signal processor system is also disposed on the first processing chip. The data processing method further comprises the following steps:

S500: the control image signal processor system preprocesses the first type of initial service data to generate the first type of service data. The preprocessing is used for removing noise data and generating a preset data format.

S600: the control image signal processor system preprocesses the second type of initial service data to generate second type of service data.

As another embodiment of the present invention, the dynamic random access memory in the first processing chip is also in communication with an external flash memory. The flash memory is used for writing the data in the dynamic random access memory into the self memory and writing the data in the self memory into the dynamic random access memory.

As another embodiment of the present invention, a sensor abnormality detection system is further disposed on the first processing chip. The sensor abnormality detection system is in communication with the image signal processor system. The data processing method further comprises the following steps:

s700: and controlling the sensor abnormality detection system to detect whether the target sensor is abnormal according to the first type of service data and the second type of service data.

As another embodiment of the present invention, a sensor abnormality detection system is configured to:

Correspondingly, the control sensor abnormality detection system detects whether the target sensor is abnormal according to the first-class service data and the second-class service data, and comprises the following steps: and controlling the sensor abnormality detection system to perform abnormality detection on each preset information acquisition component, and generating sensor abnormality information under the condition that any information acquisition component is abnormal.

As another embodiment of the present invention, the intelligent driving domain system is configured to:

In one embodiment, the method further comprises: and under the condition that a preset auxiliary driving activating instruction is acquired, the intelligent driving domain control system executes a corresponding auxiliary driving task and stops processing the first type of business data.

In one embodiment, the method further comprises: and under the condition that a preset auxiliary driving closing instruction is acquired, the intelligent driving domain control system starts to process the first type of service data and writes the first target result data into the dynamic random access memory.

As another embodiment of the invention, the cabin domain system is configured to:

In one embodiment, the method further comprises: and under the condition that the intelligent driving domain system acquires a preset auxiliary driving closing instruction, the control cabin domain system processes the second type of service data and writes second target result data into the dynamic random access memory.

As another embodiment of the present invention, the first processing chip further has a data sharing system disposed thereon. The data processing method further comprises the following steps:

s800: the control data sharing system calls the first processing core to read the first target result data and the second target result data stored in the dynamic random access memory and send the first target result data and the second target result data to the target position.

As another embodiment of the present invention, a data sharing system is configured to:

Accordingly, in one embodiment, the method further includes: and under the condition that the intelligent driving domain system acquires a preset auxiliary driving activating instruction, controlling the data sharing system to stop sending the first target result data and the second target result data in the dynamic random access memory to the target address.

Accordingly, in one embodiment, the method further includes: and under the condition that the intelligent driving domain system acquires a preset auxiliary driving closing instruction, controlling the data sharing system to start sending the first target result data and the second target result data in the dynamic random access memory to the target address.

As another embodiment of the present invention, the present invention is applied to a data processing system of a vehicle. The first type of service data at least comprises image data of a surrounding camera and a front camera of the vehicle, and the second type of service data at least comprises image data of a surrounding camera of the vehicle.

Furthermore, although the steps of the methods in the present disclosure are depicted in a particular order in the drawings, this does not require or imply that the steps must be performed in that particular order or that all illustrated steps be performed in order to achieve desirable results. Additionally or alternatively, certain steps may be omitted, multiple steps combined into one step to perform, and/or one step decomposed into multiple steps to perform, etc.

From the above description of embodiments, those skilled in the art will readily appreciate that the example embodiments described herein may be implemented in software, or may be implemented in software in combination with the necessary hardware. Thus, the technical solution according to the embodiments of the present disclosure may be embodied in the form of a software product, which may be stored in a non-volatile storage medium (may be a CD-ROM, a U-disk, a mobile hard disk, etc.) or on a network, including several instructions to cause a computing device (may be a personal computer, a server, a mobile terminal, or a network device, etc.) to perform the method according to the embodiments of the present disclosure.

In an exemplary embodiment of the present disclosure, an electronic device capable of implementing the above method is also provided.

Those skilled in the art will appreciate that the various aspects of the invention may be implemented as a system, method, or program product. Accordingly, aspects of the invention may be embodied in the following forms, namely: an entirely hardware embodiment, an entirely software embodiment (including firmware, micro-code, etc.) or an embodiment combining hardware and software aspects may be referred to herein as a "circuit," module "or" system.

An electronic device according to this embodiment of the invention. The electronic device is merely an example, and should not impose any limitations on the functionality and scope of use of embodiments of the present invention.

The electronic device is in the form of a general purpose computing device. Components of an electronic device may include, but are not limited to: the at least one processor, the at least one memory, and a bus connecting the various system components, including the memory and the processor.

Wherein the memory stores program code that is executable by the processor to cause the processor to perform steps according to various exemplary embodiments of the present invention described in the above section of the exemplary method of this specification.

The storage may include readable media in the form of volatile storage, such as Random Access Memory (RAM) and/or cache memory, and may further include Read Only Memory (ROM).

The storage may also include a program/utility having a set (at least one) of program modules including, but not limited to: an operating system, one or more application programs, other program modules, and program data, each or some combination of which may include an implementation of a network environment.

The bus may be one or more of several types of bus structures including a memory bus or memory controller, a peripheral bus, an accelerated graphics port, a processor, or a local bus using any of a variety of bus architectures.

The electronic device may also communicate with one or more external devices (e.g., keyboard, pointing device, bluetooth device, etc.), with one or more devices that enable a user to interact with the electronic device, and/or with any device (e.g., router, modem, etc.) that enables the electronic device to communicate with one or more other computing devices. Such communication may be through an input/output (I/O) interface. And, the electronic device may also communicate with one or more networks such as a Local Area Network (LAN), a Wide Area Network (WAN), and/or a public network, such as the Internet, through a network adapter. The network adapter communicates with other modules of the electronic device via a bus. It should be appreciated that although not shown, other hardware and/or software modules may be used in connection with an electronic device, including but not limited to: microcode, device drivers, redundant processors, external disk drive arrays, RAID systems, tape drives, data backup storage systems, and the like.

From the above description of embodiments, those skilled in the art will readily appreciate that the example embodiments described herein may be implemented in software, or may be implemented in software in combination with the necessary hardware. Thus, the technical solution according to the embodiments of the present disclosure may be embodied in the form of a software product, which may be stored in a non-volatile storage medium (may be a CD-ROM, a U-disk, a mobile hard disk, etc.) or on a network, including several instructions to cause a computing device (may be a personal computer, a server, a terminal device, or a network device, etc.) to perform the method according to the embodiments of the present disclosure.

In an exemplary embodiment of the present disclosure, a computer-readable storage medium having stored thereon a program product capable of implementing the method described above in the present specification is also provided. In some possible embodiments, the aspects of the present invention may also be implemented in the form of a program product comprising program code for causing a terminal device to carry out the steps according to the various exemplary embodiments of the invention as described in the "exemplary method" section of this specification, when the program product is deployed on a terminal device.

The program product may employ any combination of one or more readable media. The readable medium may be a readable signal medium or a readable storage medium. The readable storage medium can be, for example, but is not limited to, an electronic, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or a combination of any of the foregoing. More specific examples (a non-exhaustive list) of the readable storage medium would include the following: an electrical connection having one or more wires, a portable disk, a hard disk, random Access Memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM or flash memory), optical fiber, portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing.

The computer readable signal medium may include a data signal propagated in baseband or as part of a carrier wave with readable program code embodied therein. Such a propagated data signal may take any of a variety of forms, including, but not limited to, electro-magnetic, optical, or any suitable combination of the foregoing. A readable signal medium may also be any readable medium that is not a readable storage medium and that can communicate, propagate, or transport a program for use by or in connection with an instruction execution system, apparatus, or device.

Program code embodied on a readable medium may be transmitted using any appropriate medium, including but not limited to wireless, wireline, optical fiber cable, RF, etc., or any suitable combination of the foregoing.

Program code for carrying out operations of the present invention may be written in any combination of one or more programming languages, including an object oriented programming language such as Java, C++ or the like and conventional procedural programming languages, such as the "C" programming language or similar programming languages. The program code may execute entirely on the user's computing device, partly on the user's device, as a stand-alone software package, partly on the user's computing device, partly on a remote computing device, or entirely on the remote computing device or server. In the case of remote computing devices, the remote computing device may be connected to the user computing device through any kind of network, including a Local Area Network (LAN) or a Wide Area Network (WAN), or may be connected to an external computing device (e.g., connected via the Internet using an Internet service provider).

Furthermore, the above-described drawings are only schematic illustrations of processes included in the method according to the exemplary embodiment of the present invention, and are not intended to be limiting. It will be readily appreciated that the processes shown in the above figures do not indicate or limit the temporal order of these processes. In addition, it is also readily understood that these processes may be performed synchronously or asynchronously, for example, among a plurality of modules.

It should be noted that although in the above detailed description several modules or units of a device for action execution are mentioned, such a division is not mandatory. Indeed, the features and functionality of two or more modules or units described above may be embodied in one module or unit in accordance with embodiments of the present disclosure. Conversely, the features and functions of one module or unit described above may be further divided into a plurality of modules or units to be embodied.

The present invention is not limited to the above embodiments, and any changes or substitutions that can be easily understood by those skilled in the art within the technical scope of the present invention are intended to be included in the scope of the present invention. Therefore, the protection scope of the invention is subject to the protection scope of the claims.

Claims

1. A chip based on HPC system is characterized in that,

the chip is internally provided with a dynamic random access memory; the intelligent driving domain system and the cabin domain system are deployed on the chip;

the intelligent driving domain system is used for processing the first type of service data and generating first target result data; the cabin domain system is used for processing the second class of service data to generate second target result data; the first type of service data is not identical to the second type of service data;

The intelligent driving domain system is used for writing the first target result data into the dynamic random access memory and reading the first target result data and/or the second target result data;

2. The HPC system-based chip of claim 1, wherein at least one first processing core and at least one second processing core are disposed in the chip; the first processing core and the second processing core are both in communication connection with the dynamic random access memory;

the first processing core is used for being called by the intelligent driving domain system to finish processing the first type of service data and generate the first target result data; and the second processing core is used for being called by the cabin domain system to finish processing the second class of service data and generate the second target result data.

3. The HPC system-based chip of claim 1, further comprising:

an image signal processor system disposed on the chip; the method comprises the steps of preprocessing first-class initial service data to generate first-class service data; the preprocessing is used for removing noise data and generating a preset data format;

4. The HPC system-based chip of claim 1, further comprising:

5. A HPC system-based chip in accordance with claim 3, further comprising:

the sensor abnormality detection system is arranged on the chip and is in communication connection with the image signal processor system; and the system is used for detecting whether the target sensor is abnormal according to the first-class service data and the second-class service data.

6. The HPC system-based chip of claim 5, wherein the sensor anomaly detection system is configured to:

7. The HPC system-based chip of claim 1, wherein the intelligent driving domain system is configured to:

Under the condition that a preset auxiliary driving activating instruction is acquired, executing a corresponding auxiliary driving task, and stopping processing the first type of service data;

8. The HPC system-based chip of claim 1, wherein the cabin domain system is configured to:

and under the condition that the intelligent driving domain system acquires a preset auxiliary driving closing instruction, processing second-class service data, and writing second target result data into the dynamic random access memory.

9. The HPC system-based chip of any one of claims 1-8, further comprising:

the data sharing system is deployed on the chip, and calls a first processing core to read the first target result data and the second target result data stored in the dynamic random access memory and send the first target result data and the second target result data to a target position.

10. The HPC system-based chip of claim 9, wherein the data sharing system is configured to:

Under the condition that the intelligent driving domain system acquires a preset auxiliary driving activating instruction, the data sharing system stops sending first target result data and second target result data in the dynamic random access memory to a target address;

and under the condition that the intelligent driving domain system acquires a preset auxiliary driving closing instruction, the data sharing system starts to send the first target result data and the second target result data in the dynamic random access memory to a target address.

11. An HPC system-based chip according to any one of claims 1-8 or 10, applied to a data processing system of a vehicle; the first type of service data at least comprises image data of a surrounding camera and a front camera of the vehicle, and the second type of service data at least comprises image data of a surrounding camera of the vehicle.

12. A vehicle comprising a chip based on an HPC system according to any of claims 1-11.

13. The data processing method based on the HPC system is applied to a first processing chip, wherein a dynamic random access memory is arranged in the first processing chip; the intelligent driving domain system and the cabin domain system are deployed on the first processing chip;

The data processing method comprises the following steps:

controlling the intelligent driving domain system to process the first type of service data to generate first target result data;

controlling the cabin domain system to process the second class of service data to generate second target result data; the first type of service data is not identical to the second type of service data;

controlling the intelligent driving domain system to write the first target result data into the dynamic random access memory, and reading the first target result data and/or the second target result data;

and controlling the cabin domain system to write the second target result data into the dynamic random access memory, and reading the first target result data and/or the second target result data.

14. A non-transitory computer readable storage medium storing a computer program which, when executed by a processor, implements a data processing method based on an HPC system as claimed in claim 13.

15. An electronic device comprising a memory, a processor and a computer program stored in the memory and executable on the processor, wherein the processor implements a data processing method based on an HPC system as claimed in claim 13 when executing the computer program.