CN111400240A - Circuit board and artificial intelligence edge computing embedded controller - Google Patents
Circuit board and artificial intelligence edge computing embedded controller Download PDFInfo
- Publication number
- CN111400240A CN111400240A CN202010170749.6A CN202010170749A CN111400240A CN 111400240 A CN111400240 A CN 111400240A CN 202010170749 A CN202010170749 A CN 202010170749A CN 111400240 A CN111400240 A CN 111400240A
- Authority
- CN
- China
- Prior art keywords
- circuit board
- interface
- module
- board
- network card
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F15/00—Digital computers in general; Data processing equipment in general
- G06F15/76—Architectures of general purpose stored program computers
- G06F15/78—Architectures of general purpose stored program computers comprising a single central processing unit
- G06F15/7896—Modular architectures, e.g. assembled from a number of identical packages
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F1/00—Details not covered by groups G06F3/00 - G06F13/00 and G06F21/00
- G06F1/26—Power supply means, e.g. regulation thereof
- G06F1/32—Means for saving power
- G06F1/3203—Power management, i.e. event-based initiation of a power-saving mode
- G06F1/3234—Power saving characterised by the action undertaken
- G06F1/3293—Power saving characterised by the action undertaken by switching to a less power-consuming processor, e.g. sub-CPU
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F13/00—Interconnection of, or transfer of information or other signals between, memories, input/output devices or central processing units
- G06F13/38—Information transfer, e.g. on bus
- G06F13/42—Bus transfer protocol, e.g. handshake; Synchronisation
- G06F13/4282—Bus transfer protocol, e.g. handshake; Synchronisation on a serial bus, e.g. I2C bus, SPI bus
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02D—CLIMATE CHANGE MITIGATION TECHNOLOGIES IN INFORMATION AND COMMUNICATION TECHNOLOGIES [ICT], I.E. INFORMATION AND COMMUNICATION TECHNOLOGIES AIMING AT THE REDUCTION OF THEIR OWN ENERGY USE
- Y02D10/00—Energy efficient computing, e.g. low power processors, power management or thermal management
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Engineering & Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Computer Hardware Design (AREA)
- Power Sources (AREA)
Abstract
The invention provides a circuit board and an artificial intelligence edge computing embedded controller, wherein the circuit board is used for the artificial intelligence edge computing embedded controller and comprises: the core board comprises a central processing unit, and the central processing unit is an ARM processor; the mainboard is connected with the core board, and a plurality of module interfaces are arranged on the mainboard. The circuit board disclosed by the invention has the advantages of small volume and low power consumption, can meet different requirements of different customers, and saves the cost.
Description
Technical Field
The invention relates to the field of artificial intelligence equipment, in particular to a circuit board and an artificial intelligence edge computing embedded controller.
Background
With the rapid development of artificial intelligence technology in recent years, the demand for computing power of a computing platform is higher and higher, common artificial intelligence algorithms such as deep learning inference operation and the like are generally operated by means of a high-performance central processing unit, a common intel (intel) processor and the like, but the problems of high cost, high power consumption, large size, stability and reliability and the like exist, and the large-scale landing of artificial intelligence in marginal scenes is limited.
Moreover, in the current market, an artificial intelligence edge computing embedded controller usually faces all customers, the selectivity of the customers is poor, the product cost is high, and the purchase willingness of the customers is reduced.
Disclosure of Invention
In view of this, the invention provides a circuit board and an artificial intelligence edge computing embedded controller, which have small volume and low power consumption, can meet different requirements of different customers, and save cost.
To solve the above technical problem, in one aspect, the present invention provides a circuit board, including:
the core board comprises a central processing unit, and the central processing unit is an ARM processor;
the mainboard is connected with the core board, and a plurality of module interfaces are arranged on the mainboard.
Further, the core board has a plurality of blocks, each of the core boards processes a different computing task and is capable of data exchange,
alternatively, the plurality of core boards are set to a master-slave mode, respectively.
Further, a graphics processor is built in the core board.
Further, the module interface includes one or more of a camera card interface, a sound card interface, a network card interface, a USB expansion card interface, a communication interface, a hard disk interface, a patch panel interface, and a power supply network card interface, and each of the module interfaces includes one or more.
The camera interface is connected with the image processor, and the conversion chip is used for deserializing serial data from the camera and inputting the deserialized data into the image processor for processing.
The system further comprises a plurality of modules, wherein the modules correspond to the module interfaces, and the modules comprise one or more of a camera card, a sound card, a network card, a USB expansion card, a hard disk, a switching board and a power supply network card.
Furthermore, the adapter board interface includes a PCIE gold finger interface, the adapter board includes a PCIE adapter board, the network card includes a gigabit network card, and the gigabit network card is accessed to the PCIE gold finger interface through the PCIE adapter board.
Further, the main board further includes:
the synchronous time service circuit module is used for correcting the deviation according to the signal of the GPS module so as to carry out time service synchronization on the sensor accessed to the circuit board.
Further, the main board further includes:
and the temperature adjusting module is connected with the circuit board and is used for adjusting the temperature of the circuit board.
In another aspect, the present invention provides an artificial intelligence edge computing embedded controller, including:
the circuit board is any one of the circuit boards;
a chassis having a cavity to house the circuit board.
The technical scheme of the invention at least has one of the following beneficial effects:
the circuit board comprises the ARM processor, so that the power consumption is low, and the small size can be realized;
according to the circuit board, the plurality of module interfaces are arranged on the main board, so that modules can be selected and matched according to different customers, and the customer cost is saved.
Drawings
Fig. 1 is a schematic structural diagram of a circuit board according to an embodiment of the invention;
FIG. 2 is a block diagram of an artificial intelligence edge computing embedded controller according to an embodiment of the invention.
Reference numerals:
100. a core board; 200. a main board; 1000. a circuit board; 2000. a housing; 3000. an artificial intelligence edge computing embedded controller.
Detailed Description
In order to make the objects, technical solutions and advantages of the embodiments of the present invention clearer, the technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the drawings of the embodiments of the present invention. It is to be understood that the embodiments described are only a few embodiments of the present invention, and not all embodiments. All other embodiments, which can be derived by a person skilled in the art from the described embodiments of the invention, are within the scope of the invention.
Unless defined otherwise, technical or scientific terms used herein shall have the ordinary meaning as understood by one of ordinary skill in the art to which this invention belongs. The use of "first," "second," and similar terms in the present application do not denote any order, quantity, or importance, but rather the terms are used to distinguish one element from another. Also, the use of the terms "a" or "an" and the like do not denote a limitation of quantity, but rather denote the presence of at least one. The terms "connected" or "coupled" and the like are not restricted to physical or mechanical connections, but may include electrical connections, whether direct or indirect. "upper", "lower", "left", "right", and the like are used merely to indicate relative positional relationships, and when the absolute position of the object being described is changed, the relative positional relationships are changed accordingly.
Next, a circuit board 1000 according to an embodiment of the present invention is first explained with reference to the drawings.
Fig. 1 shows an alternative embodiment of a circuit board 1000 according to the present invention.
As shown in fig. 1, a circuit board 1000 according to the present invention for an artificial intelligence edge computing embedded controller 3000 includes: core board 100 and motherboard 200.
The motherboard 200 includes a Central Processing Unit (CPU), which is an arm (advanced riscmachines) processor.
Because the ARM processor consumes less power, less heat dissipation is required. Therefore, the artificial intelligence edge computing embedded controller 3000 does not need to be internally provided with a fan and/or reserve an air path, so that the assembly relationship of the internal functional modules is very compact, and the volume is reduced.
The motherboard 200 is connected to the core board 100, and the motherboard 200 is provided with a plurality of module interfaces.
That is, the main board 200 is provided with a plurality of module interfaces for interfacing a plurality of modules. From this, can be according to different customer match modules, carry out the customization according to customer's demand, when accurately satisfying customer's demand, reduce cost by a wide margin through the match, avoided the user to pay for the module that does not need.
According to some embodiments of the present invention, there are a plurality of core boards 100, each core board 100 handles different computational tasks and is capable of data exchange, or the plurality of core boards 100 are set to a master-slave mode, respectively.
For example, the core board 100 has 2 blocks, and the 2 blocks of the core board 100 may work in a master-slave mode, or may respectively execute different computing tasks, and perform data exchange through a PCIE (peripheral component interconnect express) interface.
Thus, an appropriate number of core boards 100 may be selected based on the computing power required by the customer and the need for stability. The stability of the circuit board 1000 is ensured by the plurality of core boards 100, when one core board 100 is damaged accidentally, other normal core boards 100 can perform some basic operations, so that the whole circuit board 1000 cannot fail suddenly, and particularly, some important data are processed, so that the loss of customers can be reduced. The multiple core boards 100 also work relatively efficiently, especially for multitasking.
According to some embodiments of the present invention, the core board 100 has a Graphics Processor (GPU) built therein, and the GPU is capable of processing more complex graphics. The core board 100 may adopt a system architecture of ARM CPU plus GPU acceleration, which can achieve higher operation capability and low power consumption.
Further, the module interface may include one or more of: the system comprises a camera card interface, a sound card interface, a network card interface, a USB expansion card interface, a communication interface, a hard disk interface, a patch panel interface, a power supply network card interface and the like, wherein each module interface comprises one or more interfaces.
For example, the motherboard 200 is configured with 2 gigabit network card interfaces, 1 RS232 interface, 3 RS485 interfaces (wherein 1 RS485 interface supports Profibus (field bus technology) communication protocol), 3 RS422 interfaces, 2 CAN signal interfaces, 5 USB3.0 interfaces, 2 USB2.0 interfaces, GPIO interfaces, and 8 camera interfaces (8 camera interfaces CAN basically meet the mainstream requirements of the current user). Further, the circuit board 1000 also includes a plurality of modules, the modules corresponding to the module interfaces, and the modules may include one or more of the following: camera card, sound card, network card, USB expansion card, hard disk, keysets and power supply network card.
Therefore, the corresponding modules can be selected according to the customer requirements, and customization is achieved.
Optionally, the adapter board interface includes a PCIE gold finger interface, the adapter board includes a PCIE adapter board, the network card includes a gigabit network card, and the gigabit network card is accessed to the PCIE gold finger interface through the PCIE adapter board.
Therefore, the PCIE network card can be selectively matched according to the requirements of the client, when the client almost does not need the ten-million network card subsequently, only the PCIE golden finger interface on the mainboard 200 can be reserved, when the client possibly needs the ten-million network card subsequently, the PCIE pinboard can be selectively matched, and when the client needs the ten-million network card currently, the PCIE pinboard and the ten-million network card can be selectively matched.
According to some embodiments of the present invention, the circuit board 1000 may further include a conversion chip, the conversion chip is connected to the camera interface, and the conversion chip is configured to deserialize serial data from the camera and input the deserialized data into the central processing unit for processing.
Alternatively, the chip and camera interface may be connected by a coaxial cable.
In order to meet the requirement of long-distance video transmission, a transfer chip of a gigabit multimedia serial link (GMS) L2 protocol can be adopted, camera serial data adopting the same protocol is received from a camera end, deserialized by the chip and converted into MIPI signals, and the MIPI signals are sent to the MIPI interface of the CPU, so that the long-distance transmission of the video signals through a coaxial cable is realized.
Therefore, the conversion chip can transmit long-distance video signals and can be provided for customers needing long-distance video signal transmission to carry out matching.
According to some embodiments of the present invention, the main board 200 further includes a GPS module and a synchronous time service circuit module, and the synchronous time service circuit module performs deviation rectification according to a signal of the GPS module to perform time service synchronization on the sensor in the circuit board 1000.
The sensor may include, for example, a camera, radar, etc.
Therefore, when a customer needs a plurality of sensors (such as 8 cameras and 2 radars) to operate in a precise cooperation mode, the module can enable the sensors to operate synchronously, and synchronous and more precise information is obtained.
According to some embodiments of the present invention, the main board 200 further includes a temperature adjustment module, which is connected to the circuit board 1000 for adjusting the temperature of the circuit board 1000.
The temperature adjustment module may include one or more of: heaters, refrigerators, fans, etc.
For example, customers may choose to use in high temperature areas with fans and/or refrigerators.
Therefore, the condition that a customer needs to use the circuit board 1000 in an extreme environment (with overhigh or overlow temperature) can be met by matching the temperature adjusting module, and the circuit board 1000 still runs well in the extreme environment through the temperature adjusting module.
In addition, the embodiment of the present invention further provides an artificial intelligence edge computing embedded controller 3000, which includes a circuit board 1000 and a housing 2000.
The circuit board 1000 is any of the circuit boards 1000 described above.
The cavity of the chassis 2000 accommodates the circuit board 1000.
Therefore, the embedded controller 3000 of the artificial intelligence edge computing has small volume and low power consumption, can meet different requirements of different customers, and saves cost.
While the foregoing is directed to the preferred embodiment of the present invention, it will be understood by those skilled in the art that various changes and modifications may be made without departing from the spirit and scope of the invention as defined in the appended claims.
Claims (10)
1. A circuit board (1000) for an artificial intelligence edge computing embedded controller (3000), comprising:
the core board (100), the core board (100) includes a central processing unit, the central processing unit is an ARM processor;
mainboard (200), mainboard (200) connect core board (100), be equipped with a plurality of module interfaces on mainboard (200).
2. The circuit board (1000) of claim 1, wherein the core board (100) has a plurality of blocks, each of the core boards (100) handling a different computational task and being capable of data exchange,
alternatively, the plurality of core boards (100) are set to a master-slave mode, respectively.
3. The circuit board (1000) of claim 1, wherein the core board (100) has a graphics processor built in.
4. The circuit board (1000) of claim 3, wherein the module interface comprises one or more of a camera card interface, a sound card interface, a network card interface, a USB expansion card interface, a communication interface, a hard disk interface, a patch panel interface, and a power supply network card interface, each of the module interfaces comprising one or more.
5. The circuit board (1000) of claim 4, further comprising a conversion chip coupled to the camera interface, the conversion chip configured to deserialize serial data from a camera and input the deserialized data to the graphics processor for processing.
6. The circuit board (1000) of claim 4, further comprising a plurality of modules corresponding to the module interfaces, the modules comprising one or more of a camera card, a sound card, a network card, a USB expansion card, a hard disk, a patch panel, and a power network card.
7. The circuit board (1000) of claim 5, wherein the interposer interface comprises a PCIE golden finger interface, the interposer comprises a PCIE interposer, the network card comprises a gigabit network card, and the gigabit network card is accessed to the PCIE golden finger interface through the PCIE interposer.
8. The circuit board (1000) of claim 1, wherein the motherboard (200) further comprises:
the device comprises a GPS module and a synchronous time service circuit module, wherein the synchronous time service circuit module is used for correcting the deviation according to the signal of the GPS module so as to carry out time service synchronization on a sensor accessed to the circuit board (1000).
9. The circuit board (1000) of claim 1, wherein the motherboard (200) further comprises:
the temperature adjusting module is connected with the circuit board (1000) and used for adjusting the temperature of the circuit board (1000).
10. An artificial intelligence edge computing embedded controller (3000), comprising:
-a circuit board (1000), said circuit board (1000) being a circuit board (1000) according to any of the preceding claims 1 to 9;
a chassis (2000), a cavity of the chassis (2000) accommodating the circuit board (1000).
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010170749.6A CN111400240A (en) | 2020-03-12 | 2020-03-12 | Circuit board and artificial intelligence edge computing embedded controller |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010170749.6A CN111400240A (en) | 2020-03-12 | 2020-03-12 | Circuit board and artificial intelligence edge computing embedded controller |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN111400240A true CN111400240A (en) | 2020-07-10 |
Family
ID=71432372
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202010170749.6A Pending CN111400240A (en) | 2020-03-12 | 2020-03-12 | Circuit board and artificial intelligence edge computing embedded controller |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN111400240A (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113407482A (en) * | 2021-07-14 | 2021-09-17 | 深圳思悦创新有限公司 | Customizable embedded type AI model floor hardware architecture |
Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103616935A (en) * | 2013-12-06 | 2014-03-05 | 江南大学 | Embedded computer mainboard |
| CN107909057A (en) * | 2017-11-30 | 2018-04-13 | 广东欧珀移动通信有限公司 | Image processing method, device, electronic equipment and computer-readable recording medium |
| CN208351382U (en) * | 2018-06-25 | 2019-01-08 | 浙江启扬智能科技有限公司 | Embedded main board and its core board |
| CN110032540A (en) * | 2019-04-11 | 2019-07-19 | 北京宙心科技有限公司 | A kind of artificial intelligence edge calculations equipment |
-
2020
- 2020-03-12 CN CN202010170749.6A patent/CN111400240A/en active Pending
Patent Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103616935A (en) * | 2013-12-06 | 2014-03-05 | 江南大学 | Embedded computer mainboard |
| CN107909057A (en) * | 2017-11-30 | 2018-04-13 | 广东欧珀移动通信有限公司 | Image processing method, device, electronic equipment and computer-readable recording medium |
| CN208351382U (en) * | 2018-06-25 | 2019-01-08 | 浙江启扬智能科技有限公司 | Embedded main board and its core board |
| CN110032540A (en) * | 2019-04-11 | 2019-07-19 | 北京宙心科技有限公司 | A kind of artificial intelligence edge calculations equipment |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113407482A (en) * | 2021-07-14 | 2021-09-17 | 深圳思悦创新有限公司 | Customizable embedded type AI model floor hardware architecture |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| US6057863A (en) | Dual purpose apparatus, method and system for accelerated graphics port and fibre channel arbitrated loop interfaces | |
| US9654342B2 (en) | Bandwidth configurable IO connector | |
| CN204065979U (en) | One exempts from instrument dismounting PCIE adapter | |
| US20110043989A1 (en) | Motherboard and portable electronic device using the same | |
| CN110764585B (en) | Universal independent BMC board card | |
| CN103616935A (en) | Embedded computer mainboard | |
| US20060104289A1 (en) | Multiplexed computer peripheral connection switching interface | |
| CN114661099A (en) | Mainboard, processor board card and computing system | |
| CN111400240A (en) | Circuit board and artificial intelligence edge computing embedded controller | |
| CN112000545A (en) | Graphics processor board card and graphics processor management method | |
| US8135895B2 (en) | Virtual SATA port multiplier, virtual SATA device, SATA system and data transfer method in a SATA system | |
| US8364880B2 (en) | Integrated transmission circuit and method using a media access control circuit that collectively encodes data from two distinct application circuits | |
| CN216352292U (en) | Server mainboard and server | |
| CN113741648A (en) | Computer hardware system | |
| CN112783814B (en) | Clock circuit, electronic device and method for multi-mode PCIE spread spectrum | |
| CN112988636B (en) | System, board card and electronic equipment for data acceleration processing | |
| CN204189089U (en) | A kind of server | |
| US6804737B2 (en) | Methods and systems for intelligent I/O controller with channel expandability via master/slave configuration | |
| CN216286659U (en) | High-speed data processing equipment based on homemade VPX framework | |
| CN220137687U (en) | ARM server management system | |
| CN219304904U (en) | Three-dimensional vision development board and vision perception equipment | |
| CN220962806U (en) | Medical imaging system | |
| CN110955629B (en) | Computing device | |
| CN218181515U (en) | Calculation board card and computer equipment | |
| CN212990087U (en) | KVM equipment with remote control function |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20200710 |
|
| RJ01 | Rejection of invention patent application after publication |