Heterogeneous computing power sharing network method and device of intelligent computing center

Abstract

The invention provides a heterogeneous computing power sharing network method and device of an intelligent computing center, and relates to the technical field of intelligent computing centers, intelligent computing centers and computing power infrastructures. The method comprises the steps that S1, network addresses are allocated to at least two kinds of computing power units based on network connection equipment, and the at least two kinds of computing power units are heterogeneous computing power units; s2, a first identifier is set for a first network connection device corresponding to the first computing power unit, a second identifier is set for a second network connection device corresponding to the second computing power unit, and the first identifier and the second identifier are mapped; and S3, under the condition that the second network connection equipment receives the message from the first network connection equipment, sending the message to the second computing power unit through the second network connection equipment according to the mapping relationship between the first identifier and the second identifier. By means of the mode, network sharing between heterogeneous computing power units can be achieved, and the efficiency of data transmission between the computing power units is improved.

Description

Technical Field

[0001] The present invention relates to the technical field of intelligent computing centers, intelligent computing centers, and computing power infrastructure, and in particular, to a heterogeneous computing power sharing network method and device for an intelligent computing center. Background Art

[0002] With the rapid development of artificial intelligence technology, "intelligent computing centers" and "intelligent computing centers" have emerged as the times require.

[0003] An "intelligent computing center" refers to a facility that provides the required computing power, data, and algorithms for artificial intelligence applications (such as scenarios like artificial intelligence deep learning model development, model training, and model inference) by using large-scale heterogeneous computing power resources, including general computing power and intelligent computing power. An intelligent computing center encompasses facilities, hardware, and software, and can provide full-stack capabilities from underlying computing power to top-level application enablement.

[0004] The "intelligent computing center" includes but is not limited to the "intelligent computing center".

[0005] An "intelligent computing center", that is, an artificial intelligence computing center, is a type of computing power infrastructure that provides computing power services, data services, and algorithm services required for artificial intelligence applications based on artificial intelligence theory and using an artificial intelligence computing architecture.

[0006] "Computing power" is the core of "intelligent computing centers" and "intelligent computing centers". It is the ability of computer devices or computing / data centers to process information, the ability of computer hardware and software to cooperate to jointly execute a certain computing requirement, the computing ability to achieve the output of the target result by processing information data, and a new type of productive force integrating information computing power, network carrying capacity, and data storage capacity, and mainly provides services to society through computing power infrastructure.

[0007] Currently, each computing power unit constructs its own network function. Homogeneous computing power units can directly communicate with each other, but heterogeneous computing power units need to be interconnected through devices such as their respective gateways by means of forwarding or mapping, resulting in very low efficiency in transmitting data between computing power units. Summary of the Invention

[0008] The present invention provides a heterogeneous computing power sharing network method and device for an intelligent computing center to solve the problem of very low efficiency in transmitting data between computing power units.

[0009] To solve the above technical problems, the present invention is implemented as follows:

[0010] In a first aspect, the present invention provides a heterogeneous computing power sharing network method for an intelligent computing center, including:

[0011] Step S1: Assign network addresses to each of at least two computing power units based on a network connection device, where the at least two computing power units are heterogeneous computing power units;

[0012] Step S2: Set a first identifier for a first network connection device corresponding to a first computing power unit, and set a second identifier for a second network connection device corresponding to a second computing power unit, where the first computing power unit and the second computing power unit are any two of the at least two computing power units, and the first identifier is mapped to the second identifier;

[0013] Step S3: When the second network connection device receives a message from the first network connection device, send the message to the second computing power unit through the second network connection device according to the mapping relationship between the first identifier and the second identifier.

[0014] Optionally, when the at least two computing power units include a virtual computing power unit, Step S1 includes:

[0015] Step S11: Create a virtual network interface for the virtual computing power unit;

[0016] Step S12: Connect the virtual computing power unit to a pre-created layer 2 bridge device based on the virtual network interface;

[0017] Step S13: Assign a network address to the virtual computing power unit based on the layer 2 bridge device;

[0018] When the at least two computing power units include a physical computing power unit, Step S1 includes:

[0019] Step S14: Assign a network address to the physical computing power unit based on the uplink switch device of the physical computing power unit.

[0020] Optionally, when the virtual computing power unit includes a container, Step S11 includes:

[0021] Step S111: Create a layer 2 access point for the container;

[0022] When the virtual computing power unit includes a virtual machine, Step S11 includes:

[0023] Step S112: Create a virtual network card for the virtual machine.

[0024] Optionally, Step S2 includes at least one of the following:

[0025] Step S21: When the first computing unit or the second computing unit is the virtual computing unit, set the first identifier for each two-layer bridge device corresponding to the virtual computing unit;

[0026] Step S22: When the first computing unit or the second computing unit is the physical computing unit, set the second identifier for each upstream switch device corresponding to the physical computing unit.

[0027] Optionally, the at least two types of computing units are respectively located in the same or different physical devices.

[0028] Optionally, the step S3 includes:

[0029] Step S31: When the second network connection device receives the packet sent by the first network connection device, obtain the first identifier carried in the packet through the second network connection device, where the first identifier is an identifier added by the first network connection device based on the packet;

[0030] Step S32: When there is a mapping relationship between the first identifier and the second identifier, send the packet to the second computing unit through the second network connection device.

[0031] In a second aspect, the present invention provides a heterogeneous computing power sharing network device for an intelligent computing center, including:

[0032] An allocation module, configured to allocate network addresses for each of at least two types of computing units based on a network connection device, where the at least two types of computing units are heterogeneous computing units;

[0033] A setting module, configured to set a first identifier for a first network connection device corresponding to a first computing unit, and set a second identifier for a second network connection device corresponding to a second computing unit, where the first computing unit and the second computing unit are any two of the at least two types of computing units, and the first identifier is mapped to the second identifier;

[0034] A sending module, configured to, when the second network connection device receives a packet from the first network connection device, send the packet to the second computing unit through the second network connection device according to the mapping relationship between the first identifier and the second identifier.

[0035] In a third aspect, the present invention provides a server, including: a processor, a memory, and a program stored on the memory and executable on the processor, where when the program is executed by the processor, the steps of the heterogeneous computing power sharing network method for an intelligent computing center as described in the first aspect above are implemented.

[0036] Fourthly, the present invention provides a computer-readable storage medium, on which a computer program is stored. When the computer program is executed by a processor, the steps of the heterogeneous computing power sharing network method of the intelligent computing center as described in the first aspect above are realized.

[0037] Fifthly, the present invention provides a computer program product, including computer instructions. When the computer instructions are executed by a processor, the steps of the heterogeneous computing power sharing network method of the intelligent computing center as described in the first aspect above are realized.

[0038] Through the present invention, network intercommunication between heterogeneous computing power units can be realized, and the efficiency of transmitting data between computing power units is improved. BRIEF DESCRIPTION OF THE DRAWINGS

[0039] By reading the following detailed description of the preferred embodiments, various other advantages and benefits will become clear to those of ordinary skill in the art. The drawings are only for the purpose of showing the preferred embodiments and are not considered to be a limitation of the present invention. Moreover, throughout the drawings, the same reference numerals are used to represent the same components. In the drawings:

[0040] Figure 1 is a schematic flowchart of the heterogeneous computing power sharing network method of the intelligent computing center of the present invention;

[0041] Figure 2 is a schematic diagram of the heterogeneous computing power sharing network before implementing the present invention;

[0042] Figure 3 is a schematic diagram of the heterogeneous computing power sharing network of the intelligent computing center of the present invention;

[0043] Figure 4 is a schematic structural diagram of the heterogeneous computing power sharing network device of the intelligent computing center of the present invention;

[0044] Figure 5 is a schematic structural diagram of the server of the present invention. DETAILED DESCRIPTION OF THE EMBODIMENTS

[0045] Next, the technical solutions in the present invention will be clearly and completely described in conjunction with the drawings in the present invention. Obviously, the described embodiments are some, but not all, of the embodiments of the present invention. All other embodiments obtained by those of ordinary skill in the art based on the embodiments in the present invention without creative efforts fall within the protection scope of the present invention.

[0046] First, the technical terms related to the present invention will be briefly described below.

[0047] The "computing power" described in the present invention refers to: the ability of a computer device or a computing / data center to process information, which is the ability of computer hardware and software to cooperate to jointly execute a certain computing requirement, and is the computing ability to achieve the output of the target result by processing information data. It is a new type of productive force integrating information computing power, network carrying capacity, and data storage capacity, and mainly provides services to society through computing power infrastructure.

[0048] The "computational power" (Computational Power, CP) described in the present invention refers to: the ability of the data center server to process data and achieve result output, which is a comprehensive index to measure the computing ability of the data center, including general computing ability, supercomputing ability, and intelligent computing ability. The commonly used measurement unit is the number of floating-point operations per second (FLOPS, 1EFLOPS = 10^18 FLOPS), and the larger the value, the stronger the comprehensive computing ability. It is estimated that 1EFLOPS is approximately the computing power output of 5 Tianhe 2A or 500,000 mainstream server CPUs or 2 million mainstream laptops. The calculation formula is: CP = CP 通用 + CP 智能 + CP 超级 。

[0049] The "network power" (Network Power, NP) described in the present invention refers to: the performance of the data transmission ability of the computing power facility, which is a comprehensive ability including network architecture, network bandwidth, transmission delay, intelligent management and scheduling, etc., and involves network transmission inside and between data centers, and is a comprehensive index to measure the network transmission scheduling ability.

[0050] The "storage power" (Storage Power, SP) described in the present invention refers to: the comprehensive ability of the data center in four aspects of data storage capacity, performance, security and reliability, and green and low-carbon, which is a comprehensive index to measure the data storage ability of the data center, including external storage devices such as storage arrays and server internal storage devices. The commonly used measurement unit for storage capacity is exabyte (EB, 1EB = 2^60 bytes), the commonly used measurement unit for performance is the number of read and write operations per second per unit capacity (IOPS / TB, Input / Output Operations Per Second / TB), and the disaster recovery ratio is an important manifestation of security and reliability.

[0051] The "computing power infrastructure" described in the present invention refers to: a new type of information infrastructure integrating information computing power, network carrying capacity, and data storage capacity, which can realize the centralized computing, storage, transmission, and application of information.

[0052] The "new information infrastructure" described in the present invention refers to: mainly including network infrastructures such as 5G networks, fiber broadband networks, backbone networks, international communication networks, satellite Internet, etc., computing power infrastructures such as data centers, general computing power centers, intelligent computing centers, supercomputing centers, etc., and new technology facilities such as artificial intelligence, blockchain, and quantum computing.

[0053] The "computing power" described in the present invention includes: general computing power, intelligent computing power, and super computing power.

[0054] The "general computing power" described in the present invention refers to: the computing power provided by servers based on CPU (Central Processing Unit) chips, which is used to support basic general computing such as cloud computing and edge computing.

[0055] The "intelligent computing power" described in the present invention refers to: for various artificial intelligence innovation applications, a computing platform deployed on a large scale based on dedicated chips such as GPU (Graphics Processing Unit), FPGA (Field Programmable Gate Array), ASIC (Application Specific Integrated Circuit), such as natural language processing (Natural Language Processing, NLP), machine vision, etc.

[0056] The "super computing power" described in the present invention refers to: mainly the computing power provided by high-performance computing clusters such as supercomputers. It utilizes the centralized computing resources of a multi-computer system working in parallel and processes extremely complex or data-intensive problems through a dedicated operating system. It is mainly used for computing in cutting-edge scientific fields, such as planetary simulation, drug molecule design, gene analysis, etc.

[0057] The "intelligent computing center" described in the present invention refers to: a facility that mainly provides the required computing power, data, and algorithms for artificial intelligence applications (such as scenarios of artificial intelligence deep learning model development, model training, and model inference) by using large-scale heterogeneous computing power resources, including general computing power (CPU) and intelligent computing power (GPU, FPGA, ASIC, etc.). The intelligent computing center covers facilities, hardware, and software, and can provide full-stack capabilities from underlying computing power to top-level application enabling.

[0058] The "intelligent computing center" described in the present invention includes but is not limited to the "intelligent computing center".

[0059] The "intelligent computing center" described in the present invention, that is, the artificial intelligence computing center, is a type of computing power infrastructure that provides computing power services, data services, and algorithm services required for artificial intelligence applications based on artificial intelligence theory and using an artificial intelligence computing architecture.

[0060] The "computing power center" described in the present invention refers to: a facility mainly composed of infrastructure such as wind, fire, water, and electricity and IT software and hardware devices, with computing power, carrying capacity, and storage capacity, including general data centers, intelligent computing centers, supercomputing centers, etc.

[0061] The "supercomputing center" described in the present invention refers to: that is, a supercomputing data center, which is a data center based on supercomputers or large-scale computing clusters, capable of providing functions such as large-scale computing, storage, and network services, and is widely used in application scenarios such as aerospace, national defense, oil exploration, climate modeling, and genome sequencing.

[0062] The "computing power resources" described in the present invention refer to: technologies and facilities with information computing, transmission, storage, and application capabilities required for the development of the digital society, including but not limited to computing resources such as CPUs and GPUs, network resources such as switches and routers, storage resources such as storage arrays and distributed storage, security resources such as firewalls and intrusion detection systems, and support and guarantee resources such as wind, fire, water, and electricity.

[0063] The "heterogeneous computing power" described in the present invention includes: computing tasks or training programs need to be deployed and run in some different entities. These entities will provide some computing power such as CPUs, GPUs, Networks, and Storages. Heterogeneous refers to different implementation methods between "virtual machines", "containers", and "bare metals", and these three are all common computing power units.

[0064] The "network resources" described in the present invention include: common network function modules such as layer 2 networks, layer 3 networks, gateways, tunnels, load balancers, and security groups, as well as the services provided by these network functions.

[0065] The "shared network" described in the present invention refers to: through the method in the present invention, the network isolation between heterogeneous computing power units is broken through, so that different computing power units can access various network resources without difference at the level of using network resources; different computing power units can communicate with each other without difference.

[0066] The "computing power unit" described in the present invention refers to a module or entity that can provide computing power, used to execute computer tasks and process data, and the computing power unit can be a virtual machine, a container, or a bare metal.

[0067] The "virtual computing power unit" described in the present invention refers to the abstraction of physical computing resources (such as CPUs, GPUs, memory, etc.) through virtualization technology to form logical computing resource units for providing computing power. The virtual computing power unit can be a virtual machine or a container.

[0068] The "physical computing power unit" described in the present invention refers to a computing power unit provided based on physical hardware devices, which can execute computing tasks and process data, and the physical computing power unit can be bare metal.

[0069] See Figure 1 , Figure 1 which is a heterogeneous computing power sharing network method for an intelligent computing center provided by this application. As Figure 1 shown, the method includes:

[0070] Step S1: Allocate network addresses for each of at least two types of computing power units based on network connection devices, where the at least two types of computing power units are heterogeneous computing power units;

[0071] Step S2: Set a first identifier for the first network connection device corresponding to the first computing power unit, and set a second identifier for the second network connection device corresponding to the second computing power unit, where the first computing power unit and the second computing power unit are any two of the at least two types of computing power units, and the first identifier is mapped to the second identifier;

[0072] Step S3: When the second network connection device receives a message from the first network connection device, send the message to the second computing power unit through the second network connection device according to the mapping relationship between the first identifier and the second identifier.

[0073] Among them, at least two types of computing power units can include at least two heterogeneous computing power units such as bare metal, virtual machines, containers, etc., that is, they are respectively different types of computing power units. For example, at least two types of computing power units include bare metal and virtual machines, or at least two types of computing power units include virtual machines and containers, or at least two types of computing power units include three types of computing power units: bare metal, virtual machines, and containers.

[0074] Each computing power unit can correspond to a network connection device. Based on the network connection device, a network address can be allocated for each computing power unit. The network address can be, for example, a Media Access Control Address (MAC Address), an Internet Protocol Address (IP Address), etc.

[0075] The first computing power unit corresponds to the first network connection device. Based on the first network connection device, a network address can be allocated for the first computing power unit, and a first identifier can be set for the first network connection device. The network connection device can be a device used for network connection, such as a layer 2 bridge device, a switch device, etc.

[0076] The second computing power unit corresponds to the second network connection device. Based on the second network connection device, a network address can be assigned to the second computing power unit, and a second identifier can be set for the second network connection device.

[0077] Among them, the mapping between the first identifier and the second identifier can be understood as being the same, or having a specific mapping relationship, or a pre-set mapping relationship.

[0078] When the second network connection device receives a message from the first network connection device, the second network connection device determines whether there is a mapping relationship between the first identifier and the second identifier. If there is a mapping relationship, the second network connection device sends the message to the second computing power unit; if there is no mapping relationship, the second network connection device performs other processing (for example, discarding or searching for the corresponding device by other means).

[0079] The first computing power unit and the second computing power unit can be any two of at least two types of computing power units respectively. When there are more than three heterogeneous computing power units, the implementation method between any two of the three computing power units can also be as described above.

[0080] Through the above method, the network isolation between heterogeneous computing power units can be broken through, enabling different computing power units to access various network resources without difference at the level of using network resources; network sharing is achieved between different computing power units, thereby improving the efficiency of data transmission between computing power units.

[0081] Optionally, when the at least two types of computing power units include a virtual computing power unit, the step S1 includes:

[0082] Step S11: Create a virtual network interface for the virtual computing power unit;

[0083] Step S12: Connect the virtual computing power unit to a pre-created layer 2 bridge device based on the virtual network interface;

[0084] Step S13: Assign a network address to the virtual computing power unit based on the layer 2 bridge device;

[0085] When the at least two types of computing power units include a physical computing power unit, the step S1 includes:

[0086] Step S14: Assign a network address to the physical computing power unit based on the uplink switch device of the physical computing power unit.

[0087] In the case where at least two computing power units include virtual computing power units (such as virtual machines or containers, etc.), virtual network interfaces can be created for each type of virtual resource, and the virtual computing power units can be connected to a pre-created layer-2 bridge device using the virtual network interfaces, and network addresses can be assigned to each type of virtual computing power unit based on the layer-2 bridge device. Before this step, a layer-2 bridge device can be pre-created within each server node, and the created virtual computing power units can be connected to the layer-2 bridge device.

[0088] In the case where at least two computing power units include physical computing power units (such as bare metal, etc.), an upstream switch device can be obtained for each type of physical computing power unit, and network addresses can be assigned to the physical computing power units based on the upstream switch device. Among them, the upstream switch device can be understood as a switch device that connects the physical computing power unit to the upper-layer network.

[0089] Optionally, in the case where the virtual computing power unit includes a container, step S11 includes:

[0090] Step S111: Create a layer-2 access point for the container;

[0091] In the case where the virtual computing power unit includes a virtual machine, step S11 includes:

[0092] Step S112: Create a virtual network card for the virtual machine.

[0093] For different virtual resources, virtual network interfaces can be created in the above different ways, so as to connect the virtual network interfaces of the virtual computing power units to the layer-2 bridge device.

[0094] For container-class resources, a layer-2 access point can be created in the way of customizing virtual resources through a Customer Resource Definition (CRD), for example, creating a Virtual Local Area Network (VLAN) or a Virtual Extensible LAN (VXLAN).

[0095] For virtual machine-class virtual resources, a virtual network card can be created, for example, creating a Virtual Network Interface Card (vNIC).

[0096] Through the above method, each type of virtual resource and physical resource can be connected to a network connection device and network addresses can be assigned, so that network intercommunication can be achieved within the same server node. When network sharing of heterogeneous computing power units in different server nodes needs to be achieved, it can be achieved by setting the mapping relationship between the identifiers of the network connection devices.

[0097] Optionally, step S2 includes at least one of the following:

[0098] Step S21: When the first computing power unit or the second computing power unit is the virtual computing power unit, set the first identifier for the two-layer bridge device corresponding to each virtual computing power unit;

[0099] Step S22: When the first computing power unit or the second computing power unit is the physical computing power unit, set the second identifier for the upstream switch device corresponding to each physical computing power unit.

[0100] When there is a virtual computing power unit among at least two types of computing power units, set the first identifier for the two-layer bridge device corresponding to the virtual computing power unit; when there is a physical computing power unit among at least two types of computing power units, set the second identifier for the upstream switch device corresponding to the physical computing power unit.

[0101] Of course, it is also possible to set the second identifier for the two-layer bridge device corresponding to the virtual computing power unit and set the first identifier for the upstream switch device corresponding to the physical computing power unit.

[0102] When there is a mapping relationship between the first identifier and the second identifier, network intercommunication can be achieved between the two-layer bridge device and the upstream switch device.

[0103] In some alternative embodiments, if the first computing power unit and the second computing power unit are a virtual computing power unit and a physical computing power unit respectively, network intercommunication between the first computing power unit and the second computing power unit can be achieved by adding the first identifier and the second identifier to the two-layer bridge device and the upstream switch device respectively.

[0104] In some alternative embodiments, if the first computing power unit and the second computing power unit are both virtual computing power units, network intercommunication between the first computing power unit and the second computing power unit can be achieved by adding the first identifier and the second identifier to the two two-layer bridge devices respectively.

[0105] Optionally, the at least two types of computing power units are located in the same or different physical devices.

[0106] In the above manner, the physical device can be a server or other physical device. When the same or mapped identifiers are set within the same physical device, interconnection between physical device nodes can be achieved, and when the identifiers of all nodes are synchronized, network-wide intercommunication is achieved.

[0107] In this way, a heterogeneous computing power sharing network for the same or different server nodes can be achieved, improving the efficiency of data transmission between computing power units.

[0108] Optionally, step S3 includes:

[0109] Step S31: When the second network connection device receives the packet sent by the first network connection device, obtain the first identifier carried by the packet through the second network connection device, where the first identifier is an identifier added by the first network connection device based on the packet;

[0110] Step S32: When there is a mapping relationship between the first identifier and the second identifier, send the packet to the second computing power unit through the second network connection device.

[0111] In the scenario where the first computing power unit sends a packet to the second computing power unit, after the first network connection device obtains the packet, it adds a first identifier to the packet and sends the packet carrying the first identifier to the second network connection device. When the second network connection device receives the packet sent by the first network connection device, it obtains the first identifier carried by the packet, compares the first identifier with the second identifier of the second network connection device. If there is a mapping relationship between the first identifier and the second identifier, it sends the packet to the second network connection device.

[0112] As Figure 2 shown, currently, the three heterogeneous computing powers of containers, virtual machines, and physical machines can only achieve network intercommunication in their respective networks, and the network connection between these three heterogeneous computing powers can only be achieved through the forwarding method of devices such as gateways.

[0113] As Figure 3 shown, by setting up layer-2 bridge devices in virtual computing power units such as containers and virtual machines, and setting identifiers (tags) for each layer-2 bridge device, and setting tags for each uplink switch device of the bare-metal physical machine, based on the mapping relationship between the tags, the network sharing of heterogeneous computing powers between different server nodes can be achieved.

[0114] See Figure 4 , Figure 4 is a heterogeneous computing power sharing network device 400 of an intelligent computing center provided by the present invention. The device includes:

[0115] An allocation module 401, configured to allocate network addresses for each of at least two computing power units based on a network connection device, where the at least two computing power units are heterogeneous computing power units;

[0116] A setting module 402, configured to set a first identifier for a first network connection device corresponding to a first computing power unit, and set a second identifier for a second network connection device corresponding to a second computing power unit, where the first computing power unit and the second computing power unit are any two of the at least two computing power units, and the first identifier is mapped to the second identifier;

[0117] A sending module 403, configured to, when the second network connection device receives a message from the first network connection device, send the message to the second computing power unit through the second network connection device according to the mapping relationship between the first identifier and the second identifier.

[0118] Optionally, when the at least two types of computing power units include virtual computing power units, the allocation module includes:

[0119] A creation sub-module, configured to create a virtual network interface of the virtual computing power unit;

[0120] A connection sub-module, configured to connect the virtual computing power unit to a pre-created layer 2 bridge device based on the virtual network interface;

[0121] A first allocation sub-module, configured to allocate a network address for the virtual computing power unit based on the layer 2 bridge device;

[0122] When the at least two types of computing power units include physical computing power units, the allocation module includes:

[0123] A second allocation sub-module, configured to allocate a network address for the physical computing power unit based on the upstream switch device of the physical computing power unit.

[0124] Optionally, when the virtual computing power unit includes a container, the creation sub-module is specifically configured to create a layer 2 access point of the container;

[0125] When the virtual computing power unit includes a virtual machine, the creation sub-module is specifically configured to create a virtual network card of the virtual machine.

[0126] Optionally, the setting module is specifically configured to perform at least one of the following:

[0127] When the first computing power unit or the second computing power unit is the virtual computing power unit, set the first identifier for the layer 2 bridge device corresponding to each virtual computing power unit;

[0128] When the first computing power unit or the second computing power unit is the physical computing power unit, set the second identifier for the upstream switch device corresponding to each physical computing power unit.

[0129] Optionally, the at least two types of computing power units are respectively located in the same or different physical devices.

[0130] Optionally, the sending module includes:

[0131] An obtaining sub-module, configured to obtain the first identifier carried in the message through the second network connection device when the second network connection device receives the message sent by the first network connection device, where the first identifier is an identifier added by the first network connection device based on the message;

[0132] A sending sub-module, configured to send the message to the second computing unit through the second network connection device when there is a mapping relationship between the first identifier and the second identifier.

[0133] The heterogeneous computing power sharing network device of the intelligent computing center provided by the present invention can implement each process of the above-mentioned heterogeneous computing power sharing network method of the intelligent computing center. The technical features correspond one by one and can achieve the same technical effects. To avoid repetition, they will not be described here again.

[0134] It should be noted that the heterogeneous computing power sharing network device of the intelligent computing center in the present invention can be a device, or a component, an integrated circuit, or a chip in an electronic device.

[0135] Please refer to Figure 5 , the present invention also provides a server 110, including a processor 111, a memory 112, and a computer program stored on the memory 112 and executable on the processor 111. When the computer program is executed by the processor 111, it implements each process of the above-mentioned heterogeneous computing power sharing network method embodiment of the intelligent computing center and can achieve the same technical effects. To avoid repetition, they will not be described here again.

[0136] The present invention also provides a computer-readable storage medium, on which a computer program is stored. When the computer program is executed by a processor, it implements each process of the above-mentioned heterogeneous computing power sharing network method embodiment of the intelligent computing center and can achieve the same technical effects. To avoid repetition, they will not be described here again. Among them, the computer-readable storage medium is, for example, a read-only memory (ROM), a random access memory (RAM), a magnetic disk, or an optical disc, etc.

[0137] The embodiment of the present application also provides a computer program product, including computer instructions. When the computer instructions are executed by a processor, they implement the above-mentioned Figure 1 each process of the heterogeneous computing power sharing network method embodiment of the intelligent computing center shown and can achieve the same technical effects. To avoid repetition, they will not be described here again.

[0138] It should be noted that in this text, the terms "including", "comprising" or any other variants thereof are intended to cover non-exclusive inclusion, such that a process, method, article or device comprising a series of elements includes not only those elements but also other elements not expressly listed, or elements inherent to such process, method, article or device. Without further limitation, an element defined by the phrase "comprising one..." does not exclude the presence of additional identical elements in the process, method, article or device comprising that element.

[0139] From the description of the above embodiments, those skilled in the art can clearly understand that the above-described example methods can be implemented by means of software plus a necessary general hardware platform. Of course, they can also be implemented by hardware, but in many cases the former is a better implementation. Based on such an understanding, the technical solution of the present invention, in essence or the part that contributes to the prior art, can be embodied in the form of a software product. This computer software product is stored in a storage medium (such as ROM / RAM, magnetic disk, optical disk) and includes several instructions for causing a terminal (which can be a mobile phone, computer, server, air conditioner, or network device, etc.) to execute the methods described in various embodiments of the present invention.

[0140] The embodiments of the present invention have been described above in conjunction with the accompanying drawings. However, the present invention is not limited to the above specific embodiments. The above specific embodiments are merely illustrative and not restrictive. Under the inspiration of the present invention, those of ordinary skill in the art can also make many forms without departing from the spirit and scope of the present invention as protected by the claims, and all of them fall within the protection scope of the present invention.

Claims

1. A heterogeneous computing power sharing network method for an intelligent computing center, characterized in that, including: Step S1: Allocate network addresses for each of at least two computing power units based on a network connection device, where the at least two computing power units are heterogeneous computing power units; Step S2: Set a first identifier for a first network connection device corresponding to a first computing power unit, and set a second identifier for a second network connection device corresponding to a second computing power unit, where the first computing power unit and the second computing power unit are any two of the at least two computing power units, and the first identifier is mapped to the second identifier; Step S3: In the case where the second network connection device receives a message from the first network connection device, send the message to the second computing power unit through the second network connection device according to the mapping relationship between the first identifier and the second identifier.

2. The method according to claim 1, wherein In the case where the at least two computing power units include a virtual computing power unit, Step S1 includes: Step S11: Create a virtual network interface for the virtual computing power unit; Step S12: Connect the virtual computing power unit to a pre-created layer 2 bridge device based on the virtual network interface; Step S13: Allocate a network address for the virtual computing power unit based on the layer 2 bridge device; In the case where the at least two computing power units include a physical computing power unit, Step S1 includes: Step S14: Allocate a network address for the physical computing power unit based on the upstream switch device of the physical computing power unit.

3. The method according to claim 2, wherein In the case where the virtual computing power unit includes a container, Step S11 includes: Step S111: Create a layer 2 access point for the container; In the case where the virtual computing power unit includes a virtual machine, Step S11 includes: Step S112: Create a virtual network card for the virtual machine.

4. The method according to claim 2 or 3, characterized in that, Step S2 includes at least one of the following: Step S21: In the case where the first computing power unit or the second computing power unit is the virtual computing power unit, set the first identifier for the layer 2 bridge device corresponding to each virtual computing power unit; Step S22: In the case where the first computing power unit or the second computing power unit is the physical computing power unit, set the second identifier for the upstream switch device corresponding to each physical computing power unit.

5. The method according to any one of claims 1 to 3, characterized in that, The at least two computing power units are respectively located in the same or different physical devices.

6. The method according to any one of claims 1 to 3, characterized in that Step S3 includes: Step S31: In the case where the second network connection device receives a message sent by the first network connection device, obtain the first identifier carried in the message through the second network connection device, where the first identifier is an identifier added by the first network connection device based on the message; Step S32: In the case where there is a mapping relationship between the first identifier and the second identifier, send the message to the second computing power unit through the second network connection device.

7. A heterogeneous computing power sharing network device for an intelligent computing center, characterized in that, including: An allocation module for allocating network addresses for each of at least two computing power units based on a network connection device, where the at least two computing power units are heterogeneous computing power units; A setting module, configured to set a first identifier for a first network connection device corresponding to a first computing power unit and set a second identifier for a second network connection device corresponding to a second computing power unit, where the first computing power unit and the second computing power unit are any two of the at least two types of computing power units, and the first identifier is mapped to the second identifier; A sending module, configured to, when the second network connection device receives a packet from the first network connection device, send the packet to the second computing power unit through the second network connection device according to the mapping relationship between the first identifier and the second identifier.

8. A server, characterized in that, Comprising: A processor, a memory, and a program stored on the memory and executable on the processor, where when the program is executed by the processor, the steps of the heterogeneous computing power sharing network method of the intelligent computing center according to any one of claims 1 to 6 are implemented.

9. A computer-readable storage medium, characterized in that, A computer program is stored on the computer-readable storage medium, and when the computer program is executed by a processor, the steps of the heterogeneous computing power sharing network method of the intelligent computing center according to any one of claims 1 to 6 are implemented.

10. A computer program product, characterized in that, Comprising computer instructions, and when the computer instructions are executed by a processor, the steps of the heterogeneous computing power sharing network method of the intelligent computing center according to any one of claims 1 to 6 are implemented.

Images