CN114780472A - Host and PCIe device decoupling method, device, equipment and storage medium - Google Patents
Host and PCIe device decoupling method, device, equipment and storage medium Download PDFInfo
- Publication number
- CN114780472A CN114780472A CN202210465823.6A CN202210465823A CN114780472A CN 114780472 A CN114780472 A CN 114780472A CN 202210465823 A CN202210465823 A CN 202210465823A CN 114780472 A CN114780472 A CN 114780472A
- Authority
- CN
- China
- Prior art keywords
- pcie
- host
- expansion module
- target
- ethernet
- 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.)
- Withdrawn
Links
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING OR CALCULATING; 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
- G06F13/40—Bus structure
- G06F13/4004—Coupling between buses
- G06F13/4022—Coupling between buses using switching circuits, e.g. switching matrix, connection or expansion network
-
- G—PHYSICS
- G06—COMPUTING OR CALCULATING; 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
- G06F13/40—Bus structure
- G06F13/4063—Device-to-bus coupling
- G06F13/4068—Electrical coupling
-
- G—PHYSICS
- G06—COMPUTING OR CALCULATING; COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F2213/00—Indexing scheme relating to interconnection of, or transfer of information or other signals between, memories, input/output devices or central processing units
- G06F2213/0026—PCI express
Landscapes
- Engineering & Computer Science (AREA)
- General Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- Computer Hardware Design (AREA)
- General Physics & Mathematics (AREA)
- Mathematical Physics (AREA)
- Information Transfer Systems (AREA)
Abstract
本申请公开了一种主机与PCIe设备解耦方法、装置、设备及存储介质,涉及计算机技术领域,包括:将PCIe扩展模块从主机中分离,得到独立PCIe扩展模块;在独立PCIe扩展模块中,将PCIe交换机与数据处理器相连得到目标PCIe扩展模块,并通过数据处理器将目标PCIe扩展模块接入到以太网;通过内接的OCP网卡将主机接入到以太网,并通过以太网矩阵实现目标PCIe扩展模块与主机的通信。本申请在PCIe扩展模块中,添加与PCIe交换机相连的数据处理器,然后通过数据处理器将PCIe协议转换成以太网协议,并通过以太网矩阵实现解耦后的PCIe扩展模块与主机的通信和资源共享,能够降低主机的设计难度,便于主板和PCIe设备的扩展和独立升级。
The present application discloses a method, device, device and storage medium for decoupling a host from a PCIe device, and relates to the field of computer technology, including: separating a PCIe expansion module from a host to obtain an independent PCIe expansion module; in the independent PCIe expansion module, Connect the PCIe switch and the data processor to obtain the target PCIe expansion module, and connect the target PCIe expansion module to the Ethernet through the data processor; connect the host to the Ethernet through the built-in OCP network card, and implement it through the Ethernet matrix Communication between the target PCIe expansion module and the host. In the present application, a data processor connected to the PCIe switch is added to the PCIe expansion module, and then the PCIe protocol is converted into an Ethernet protocol through the data processor, and the communication and communication between the decoupled PCIe expansion module and the host are realized through the Ethernet matrix. Resource sharing can reduce the design difficulty of the host, and facilitate the expansion and independent upgrade of motherboards and PCIe devices.
Description
技术领域technical field
本申请涉及计算机技术领域,特别涉及一种主机与PCIe设备解耦方法、装置、设备及存储介质。The present application relates to the field of computer technologies, and in particular, to a method, apparatus, device, and storage medium for decoupling a host from a PCIe device.
背景技术Background technique
PCIe(Peripheral Component Interconnect-express,周边设备高速连接标准)是在PCI的基础上为实现CPU(Central Processing Unit,中央处理器)与周边设备之间更高速的通信而提出的一种连接标准,并且已经成为当前计算机系统中应用最为广泛的扩展总线。PCIe属于高速串行点对点双通道高带宽传输,所连接的设备分配独享通道带宽,不共享总线带宽,主要支持主动电源管理,错误报告,端对端的可靠性传输,热插拔以及服务质量(QoS,Quality of Service)等功能。PCIe (Peripheral Component Interconnect-express, peripheral device high-speed connection standard) is a connection standard proposed on the basis of PCI to achieve higher-speed communication between CPU (Central Processing Unit, central processing unit) and peripheral devices, and It has become the most widely used expansion bus in current computer systems. PCIe belongs to high-speed serial point-to-point dual-channel high-bandwidth transmission. The connected devices allocate exclusive channel bandwidth and do not share bus bandwidth. It mainly supports active power management, error reporting, end-to-end reliable transmission, hot plugging and quality of service ( QoS, Quality of Service) and other functions.
为了减小主板的面积、降低主板成本、实现PCIe设备与主板的独立升级,通常会将PCIe设备从主板上解耦。如对通用服务器中硬盘背板的设计,通过将中央处理器的PCIe通道(lane)接出到硬盘背板上,并连接PCIe Switch(PCIe交换机),再通过PCIe Switch扩展出更多的PCIe接口,从而实现硬盘数量的扩展,增加了灵活性和可扩展性,也降低了主板设计的难度。但目前PCIe设备的解耦并不完全:一方面,一些PCIe插槽仍放置在主板上,如OCPNIC(Open Compute Project Network Interface Card,开源计算项目网络接口卡)卡插槽,GPU(Graphic Processing Unit,图形处理器)卡插槽、声卡插槽等,随着对PCIe资源需求的增大,会扩展出更多的PCIe接口;另一方面,主机与PCIe设备解耦板仍放置在主机内,与主机绑定,越多的PCIe交换机、PCIe总线、PCIe插槽等放置在主机内,占用的主机体积就越大,不利于主机的扩展,增加了主机散热设计的难度。In order to reduce the area of the mainboard, reduce the cost of the mainboard, and realize the independent upgrade of the PCIe device and the mainboard, the PCIe device is usually decoupled from the mainboard. For example, for the design of the hard disk backplane in a general server, the PCIe lane (lane) of the central processing unit is connected to the hard disk backplane, and the PCIe Switch (PCIe switch) is connected, and then more PCIe interfaces are extended through the PCIe Switch. , so as to realize the expansion of the number of hard disks, increase flexibility and expandability, and reduce the difficulty of motherboard design. However, the current decoupling of PCIe devices is not complete: on the one hand, some PCIe slots are still placed on the motherboard, such as OCPNIC (Open Compute Project Network Interface Card, Open Compute Project Network Interface Card) card slot, GPU (Graphic Processing Unit) , graphics processor) card slot, sound card slot, etc. As the demand for PCIe resources increases, more PCIe interfaces will be expanded; on the other hand, the decoupling board between the host and the PCIe device is still placed in the host. Binding with the host, the more PCIe switches, PCIe buses, PCIe slots, etc. are placed in the host, the larger the volume of the host is occupied, which is not conducive to the expansion of the host, and increases the difficulty of the heat dissipation design of the host.
因此,如何将PCIe设备从主板上解耦,并实现最大的灵活性和可扩展性是本领域技术人员需要解决的技术问题。Therefore, how to decouple the PCIe device from the motherboard and achieve maximum flexibility and scalability is a technical problem that needs to be solved by those skilled in the art.
发明内容SUMMARY OF THE INVENTION
有鉴于此,本申请的目的在于提供一种主机与PCIe设备解耦方法、装置、设备及存储介质,能够实现PCIe设备与主机的解耦,降低主机的设计难度,便于主板和PCIe设备的扩展和独立升级,并使扩展性最大化。其具体方案如下:In view of this, the purpose of this application is to provide a method, device, device and storage medium for decoupling a host and a PCIe device, which can realize the decoupling of the PCIe device and the host, reduce the design difficulty of the host, and facilitate the expansion of the motherboard and the PCIe device. and independent upgrades and maximize scalability. Its specific plan is as follows:
第一方面,本申请公开了一种主机与PCIe设备解耦方法,包括:In a first aspect, the present application discloses a method for decoupling a host from a PCIe device, including:
将PCIe扩展模块从主机中分离,得到独立PCIe扩展模块;所述独立PCIe扩展模块包括PCIe交换机和多个通过PCIe连接器与所述PCIe交换机相连的PCIe终端设备;The PCIe expansion module is separated from the host to obtain an independent PCIe expansion module; the independent PCIe expansion module includes a PCIe switch and a plurality of PCIe terminal devices connected to the PCIe switch through a PCIe connector;
在所述独立PCIe扩展模块中,将所述PCIe交换机与数据处理器相连,得到目标PCIe扩展模块,并通过所述数据处理器将所述目标PCIe扩展模块接入到以太网;In the independent PCIe expansion module, the PCIe switch is connected to a data processor to obtain a target PCIe expansion module, and the target PCIe expansion module is connected to the Ethernet through the data processor;
通过内接的OCP网卡将所述主机接入到所述以太网,并通过以太网矩阵实现所述目标PCIe扩展模块与所述主机的通信。The host is connected to the Ethernet through the built-in OCP network card, and the communication between the target PCIe expansion module and the host is implemented through an Ethernet matrix.
可选的,所述通过所述数据处理器将所述目标PCIe扩展模块接入到以太网,包括:Optionally, the connecting the target PCIe expansion module to the Ethernet through the data processor includes:
通过所述数据处理器对外提供的网口将所述目标PCIe扩展模块中的所述PCIe交换机、所述PCIe连接器和所述PCIe交换机接入到以太网。The PCIe switch, the PCIe connector and the PCIe switch in the target PCIe expansion module are connected to the Ethernet through the network port provided externally by the data processor.
可选的,所述主机与PCIe设备解耦方法,还包括:Optionally, the method for decoupling the host from the PCIe device further includes:
根据所述数据处理器的带宽和所述PCIe交换机的带宽分别对所述数据处理器的数量和所述PCIe交换机的数量进行调节。The number of the data processors and the number of the PCIe switches are adjusted respectively according to the bandwidth of the data processor and the bandwidth of the PCIe switch.
可选的,所述目标PCIe扩展模块的硬件结构由多个PCIe连接器插槽、PCIe印刷电路板、目标芯片和冷板组成;其中,所述目标芯片包括PCIe交换机芯片、数据处理器芯片和管理芯片。Optionally, the hardware structure of the target PCIe expansion module is composed of a plurality of PCIe connector slots, a PCIe printed circuit board, a target chip and a cold plate; wherein, the target chip includes a PCIe switch chip, a data processor chip and a management chip.
可选的,所述多个PCIe连接器插槽和所述目标芯片位于所述PCIe印刷电路板的正面,所述冷板位于所述PCIe印刷电路板的背面。Optionally, the plurality of PCIe connector slots and the target chip are located on the front side of the PCIe printed circuit board, and the cold plate is located on the back side of the PCIe printed circuit board.
可选的,所述主机与PCIe设备解耦方法,还包括:Optionally, the method for decoupling the host from the PCIe device further includes:
采用紧凑的堆叠结构将所述多个PCIe连接器插槽、所述目标芯片、所述冷板、电源和散热器集成在所述PCIe印刷电路板上。The plurality of PCIe connector slots, the target chip, the cold plate, the power supply and the heat sink are integrated on the PCIe printed circuit board using a compact stack structure.
可选的,所述主机与PCIe设备解耦方法,还包括:Optionally, the method for decoupling the host from the PCIe device further includes:
获取多个所述目标PCIe扩展模块,并通过所述以太网实现多个所述目标PCIe扩展模块之间及多个所述目标PCIe扩展模块与所述主机之间的互联与通信。Acquire a plurality of the target PCIe expansion modules, and implement interconnection and communication between the multiple target PCIe expansion modules and between the multiple target PCIe expansion modules and the host through the Ethernet.
第二方面,本申请公开了一种主机与PCIe设备解耦装置,包括:In a second aspect, the present application discloses an apparatus for decoupling a host from a PCIe device, including:
分离模块,用于将PCIe扩展模块从主机中分离,得到独立PCIe扩展模块;所述独立PCIe扩展模块包括PCIe交换机和多个通过PCIe连接器与所述PCIe交换机相连的PCIe终端设备;A separation module for separating the PCIe expansion module from the host to obtain an independent PCIe expansion module; the independent PCIe expansion module includes a PCIe switch and a plurality of PCIe terminal devices connected to the PCIe switch through a PCIe connector;
连接模块,用于在所述独立PCIe扩展模块中,将所述PCIe交换机与数据处理器相连,得到目标PCIe扩展模块,并通过所述数据处理器将所述目标PCIe扩展模块接入到以太网;a connection module for connecting the PCIe switch and the data processor in the independent PCIe expansion module to obtain a target PCIe expansion module, and connecting the target PCIe expansion module to the Ethernet through the data processor ;
通信模块,用于通过内接的OCP网卡将所述主机接入到所述以太网,并通过以太网矩阵实现所述目标PCIe扩展模块与所述主机的通信。The communication module is used for connecting the host to the Ethernet through the built-in OCP network card, and realizing the communication between the target PCIe expansion module and the host through the Ethernet matrix.
第三方面,本申请公开了一种电子设备,包括处理器和存储器;其中,所述处理器执行所述存储器中保存的计算机程序时实现前述的主机与PCIe设备解耦方法。In a third aspect, the present application discloses an electronic device, including a processor and a memory; wherein, when the processor executes a computer program stored in the memory, the foregoing method for decoupling a host and a PCIe device is implemented.
第四方面,本申请公开了一种计算机可读存储介质,用于存储计算机程序;其中,所述计算机程序被处理器执行时实现前述的主机与PCIe设备解耦方法。In a fourth aspect, the present application discloses a computer-readable storage medium for storing a computer program; wherein, when the computer program is executed by a processor, the aforementioned method for decoupling a host and a PCIe device is implemented.
可见,本申请先将PCIe扩展模块从主机中分离,得到独立PCIe扩展模块,然后在所述独立PCIe扩展模块中,将所述PCIe交换机与数据处理器相连,得到目标PCIe扩展模块,并通过所述数据处理器将所述目标PCIe扩展模块接入到以太网,再通过内接的OCP网卡将所述主机接入到所述以太网,并通过以太网矩阵实现所述目标PCIe扩展模块与所述主机的通信。本申请在PCIe扩展模块中,添加与PCIe交换机相连的数据处理器,然后通过数据处理器将PCIe协议转换成以太网协议,并通过以太网矩阵实现解耦后的PCIe扩展模块与主机的通信和资源共享,能够降低主机的设计难度,便于主板和PCIe设备的扩展和独立升级,并使扩展性最大化,可快速向市场推出,应用灵活。It can be seen that in the present application, the PCIe expansion module is first separated from the host to obtain an independent PCIe expansion module, and then in the independent PCIe expansion module, the PCIe switch is connected to the data processor to obtain the target PCIe expansion module, and through all the PCIe expansion modules The data processor connects the target PCIe expansion module to the Ethernet, then connects the host to the Ethernet through the built-in OCP network card, and realizes the connection between the target PCIe expansion module and the Ethernet through the Ethernet matrix. communication with the host. In the present application, a data processor connected to a PCIe switch is added to the PCIe expansion module, and then the PCIe protocol is converted into an Ethernet protocol through the data processor, and the communication and communication between the decoupled PCIe expansion module and the host are realized through the Ethernet matrix. Resource sharing can reduce the design difficulty of the host, facilitate the expansion and independent upgrade of motherboards and PCIe devices, maximize scalability, and can be quickly introduced to the market with flexible applications.
附图说明Description of drawings
为了更清楚地说明本申请实施例或现有技术中的技术方案,下面将对实施例或现有技术描述中所需要使用的附图作简单地介绍,显而易见地,下面描述中的附图仅仅是本申请的实施例,对于本领域普通技术人员来讲,在不付出创造性劳动的前提下,还可以根据提供的附图获得其他的附图。In order to more clearly illustrate the embodiments of the present application or the technical solutions in the prior art, the following briefly introduces the accompanying drawings required for the description of the embodiments or the prior art. Obviously, the drawings in the following description are only It is an embodiment of the present application. For those of ordinary skill in the art, other drawings can also be obtained according to the provided drawings without any creative effort.
图1为本申请公开的一种主机与PCIe设备解耦方法流程图;1 is a flowchart of a method for decoupling a host and a PCIe device disclosed in the present application;
图2为本申请公开的一种具体的PCIe系统拓扑示意图;2 is a schematic diagram of a specific PCIe system topology disclosed in the application;
图3为本申请公开的一种具体的解耦后的PCIe扩展模块拓扑示意图;3 is a schematic topology diagram of a specific decoupled PCIe expansion module disclosed in the present application;
图4为本申请公开的一种具体的解耦后的PCIe扩展模块硬件结构示意图;4 is a schematic diagram of the hardware structure of a specific decoupled PCIe expansion module disclosed in the present application;
图5为本申请公开的一种主机与PCIe设备解耦装置结构示意图;5 is a schematic structural diagram of a device for decoupling a host and a PCIe device disclosed in the present application;
图6为本申请公开的一种电子设备结构图。FIG. 6 is a structural diagram of an electronic device disclosed in this application.
具体实施方式Detailed ways
下面将结合本申请实施例中的附图,对本申请实施例中的技术方案进行清楚、完整地描述,显然,所描述的实施例仅仅是本申请一部分实施例,而不是全部的实施例。基于本申请中的实施例,本领域普通技术人员在没有做出创造性劳动前提下所获得的所有其他实施例,都属于本申请保护的范围。The technical solutions in the embodiments of the present application will be clearly and completely described below with reference to the drawings in the embodiments of the present application. Obviously, the described embodiments are only a part of the embodiments of the present application, but not all of the embodiments. Based on the embodiments in the present application, all other embodiments obtained by those of ordinary skill in the art without creative efforts shall fall within the protection scope of the present application.
本申请实施例公开了一种主机与PCIe设备解耦方法,参见图1所示,该方法包括:An embodiment of the present application discloses a method for decoupling a host from a PCIe device. Referring to FIG. 1 , the method includes:
步骤S11:将PCIe扩展模块从主机中分离,得到独立PCIe扩展模块;所述独立PCIe扩展模块包括PCIe交换机和多个通过PCIe连接器与所述PCIe交换机相连的PCIe终端设备。Step S11: Separate the PCIe expansion module from the host to obtain an independent PCIe expansion module; the independent PCIe expansion module includes a PCIe switch and a plurality of PCIe terminal devices connected to the PCIe switch through PCIe connectors.
本实施例中,先将包括PCIe交换机和多个通过PCIe连接器(即PCIe Connector)与上述PCIe交换机相连的PCIe终端设备(即PCIe Endpoint)的PCIe扩展模块从主机中分离出来,得到独立PCIe扩展模块。可以理解的是,PCIe总线采用的是端到端的连接方式,一条PCIe链路只能连接一个设备。因此,当主机中需要连接使用多个PCIe设备时,必须将PCIe链路进行扩展,这种扩展设备具有一个上游端口和多个下游端口。如图2所示,主机的中央处理器中的PCIe资源通过根复合体(Root Complex)接出,根复合体可以直接挂载PCIe终端设备,但由于从中央处理器的根复合体出来的PCIe资源是有限的,为了扩展PCIe资源,通常会采用PCIe交换机扩展PCIe端口,将一个PCIe端口扩展为若干个,靠近复合体的端口称为上游端口,扩展出来的端口称为下游端口,下游端口可以挂载多个PCIe终端设备或者其它PCIe交换机并对其进行管理,其中,根复合体和PCIe交换机之间是通过PCIe总线进行连接的,将PCIe扩展模块从主机中分离也即将与PCIe总线相连的PCIe交换机和与PCIe交换机相连的多个PCIe终端设备作为一个独立的模块从主机中分离。In this embodiment, a PCIe expansion module including a PCIe switch and a plurality of PCIe terminal devices (ie, PCIe Endpoints) connected to the above-mentioned PCIe switch through PCIe connectors (ie, PCIe Connectors) is first separated from the host to obtain an independent PCIe expansion module. module. It is understandable that the PCIe bus adopts an end-to-end connection method, and a PCIe link can only be connected to one device. Therefore, when multiple PCIe devices need to be connected and used in the host, the PCIe link must be extended, and this extended device has one upstream port and multiple downstream ports. As shown in Figure 2, the PCIe resources in the CPU of the host are connected through the Root Complex. The root complex can directly mount PCIe terminal devices. Resources are limited. In order to expand PCIe resources, PCIe switches are usually used to expand PCIe ports, and a PCIe port is expanded into several. The ports close to the complex are called upstream ports, and the extended ports are called downstream ports. Mount multiple PCIe terminal devices or other PCIe switches and manage them. The root complex and the PCIe switch are connected through the PCIe bus, and the PCIe expansion module is separated from the host and will be connected to the PCIe bus. The PCIe switch and multiple PCIe end devices connected to the PCIe switch are separated from the host as an independent module.
在一种具体的实施方式中,所述目标PCIe扩展模块的硬件结构可以由多个PCIe连接器插槽、PCIe印刷电路板(即PCB,Printed Circuit Board)、目标芯片和冷板组成;其中,所述目标芯片包括PCIe交换机芯片、数据处理器芯片和管理芯片,所述管理芯片包括但不限于BMC(Baseboard Management Controller,基板管理控制器)芯片等。In a specific implementation manner, the hardware structure of the target PCIe expansion module may be composed of multiple PCIe connector slots, a PCIe printed circuit board (ie PCB, Printed Circuit Board), a target chip and a cold plate; wherein, The target chip includes a PCIe switch chip, a data processor chip, and a management chip, and the management chip includes but is not limited to a BMC (Baseboard Management Controller, baseboard management controller) chip and the like.
为了进一步的最大化利用空间,实现小型化的模块构造,所述主机与PCIe设备解耦方法,还可以包括:采用紧凑的堆叠结构将所述多个PCIe连接器插槽、所述目标芯片、所述冷板、电源和散热器集成在所述PCIe印刷电路板上。即采用堆叠结构将多个PCIe连接器插槽、目标芯片、冷板、电源以及散热器等所需的器件紧凑的集成在更小的体积内。In order to further maximize the utilization of space and realize a miniaturized module structure, the method for decoupling the host from the PCIe device may further include: using a compact stack structure to connect the multiple PCIe connector slots, the target chip, The cold plate, power supply and heat sink are integrated on the PCIe printed circuit board. That is, a stack structure is used to compactly integrate multiple PCIe connector slots, target chips, cold plates, power supplies, and heat sinks into a smaller volume.
在一种具体的实施方式中,可以将上述多个PCIe连接器插槽和上述目标芯片放置在所述PCIe印刷电路板的正面,将所述冷板放置在所述PCIe印刷电路板的背面。具体的,可以在所述PCIe印刷电路板板的背面放置一块液冷板,并在上述液冷板的背面集成电源,用于对所述目标芯片及相应的PCIe设备进行散热与供电,进一步的,为了达到最优的散热效果,可以将所述液冷板和所述PCIe印刷电路板紧贴在一起。In a specific implementation manner, the above-mentioned multiple PCIe connector slots and the above-mentioned target chip may be placed on the front side of the PCIe printed circuit board, and the cold plate may be placed on the backside of the PCIe printed circuit board. Specifically, a liquid-cooling board can be placed on the back of the PCIe printed circuit board, and a power supply can be integrated on the back of the liquid-cooling board to dissipate heat and supply power to the target chip and the corresponding PCIe device, and further , in order to achieve the optimal heat dissipation effect, the liquid cooling board and the PCIe printed circuit board may be closely attached together.
步骤S12:在所述独立PCIe扩展模块中,将所述PCIe交换机与数据处理器相连,得到目标PCIe扩展模块,并通过所述数据处理器将所述目标PCIe扩展模块接入到以太网。Step S12: In the independent PCIe expansion module, connect the PCIe switch to a data processor to obtain a target PCIe expansion module, and connect the target PCIe expansion module to the Ethernet through the data processor.
本实施例中,将PCIe扩展模块从主机中分离得到独立PCIe扩展模块之后,可以在上述独立PCIe扩展模块中添加数据处理器(DPU,Data Processing Unit),然后将上述PCIe交换机与所述数据处理器相连,进一步的,通过所述数据处理器将上述目标PCIe扩展模块接入到以太网(Ethernet)中。In this embodiment, after the PCIe expansion module is separated from the host to obtain an independent PCIe expansion module, a data processor (DPU, Data Processing Unit) may be added to the independent PCIe expansion module, and then the PCIe switch and the data processing unit may be added. The above-mentioned target PCIe expansion module is connected to the Ethernet (Ethernet) through the data processor.
本实施例中,所述通过所述数据处理器将所述目标PCIe扩展模块接入到以太网,具体可以包括:通过所述数据处理器对外提供的网口将所述目标PCIe扩展模块中的所述PCIe交换机、所述PCIe连接器和所述PCIe交换机接入到以太网。也即,在将PCIe扩展模块从主机中分离得到独立PCIe扩展模块之后,数据处理器会在上述独立PCIe扩展模块上创建对外的网口,通过所述网口可以将PCIe资源,即目标PCIe扩展模块中的PCIe交换机、PCIe连接器和PCIe交换机,接入到以太网中。In this embodiment, the connecting the target PCIe expansion module to the Ethernet through the data processor may specifically include: connecting the target PCIe expansion module to an external network port provided by the data processor. The PCIe switch, the PCIe connector and the PCIe switch are connected to Ethernet. That is, after separating the PCIe expansion module from the host to obtain an independent PCIe expansion module, the data processor will create an external network port on the above-mentioned independent PCIe expansion module, through which the PCIe resource, that is, the target PCIe expansion module can be expanded. The PCIe switch, PCIe connector and PCIe switch in the module are connected to the Ethernet.
步骤S13:通过内接的OCP网卡将所述主机接入到所述以太网,并通过以太网矩阵实现所述目标PCIe扩展模块与所述主机的通信。Step S13: The host is connected to the Ethernet through the built-in OCP network card, and the communication between the target PCIe expansion module and the host is realized through an Ethernet matrix.
本实施例中,通过所述数据处理器将所述目标PCIe扩展模块接入到以太网之后,所述数据处理器还可以进一步的通过内接的OCP网卡(如OCP NIC 3.0网卡)将所述主机接入到上述以太网,然后通过以太网矩阵(Ethernet Fabric)实现上述目标PCIe扩展模块与上述主机之间的互联与通信,即实现了PCIe扩展模块与主机的数据共享与交互。In this embodiment, after the target PCIe expansion module is connected to the Ethernet through the data processor, the data processor may further connect the OCP network card (such as an OCP NIC 3.0 network card) to the The host is connected to the above-mentioned Ethernet, and then the interconnection and communication between the above-mentioned target PCIe expansion module and the above-mentioned host are realized through an Ethernet fabric, that is, data sharing and interaction between the PCIe expansion module and the host are realized.
在一种具体的实施方式中,为了给主机提供最大化的资源扩展,所述主机与PCIe设备解耦方法,还可以包括:获取多个所述目标PCIe扩展模块,并通过所述以太网实现多个所述目标PCIe扩展模块之间及多个所述目标PCIe扩展模块与所述主机之间的互联与通信。也即,采用多个PCIe扩展模块实现PCIe设备的池化,将所有PCIe设备通过PCIe交换机和数据处理器接入到以太网中,在以太网中实现多个PCIe扩展模块之间以及多个PCIe扩展模块与主机之间的互联与通信,从而为主机提供最大化的资源扩展。另外,如果增加数据处理器对外提供的网口的数量,多个PCIe扩展模块还可以接到多个主机上,从而实现多个主机访问多个PCIe扩展模块(PCIe资源池),即实现PCIe资源在多个主机之间的共享。In a specific implementation manner, in order to provide the host with maximum resource expansion, the method for decoupling the host from the PCIe device may further include: acquiring a plurality of the target PCIe expansion modules, and implementing them through the Ethernet Interconnection and communication between multiple target PCIe expansion modules and between multiple target PCIe expansion modules and the host. That is, multiple PCIe expansion modules are used to realize the pooling of PCIe devices, all PCIe devices are connected to the Ethernet through PCIe switches and data processors, and multiple PCIe expansion modules and multiple PCIe expansion modules are implemented in the Ethernet. The interconnection and communication between the expansion module and the host, so as to provide the host with maximum resource expansion. In addition, if the number of network ports provided by the data processor is increased, multiple PCIe expansion modules can also be connected to multiple hosts, so that multiple hosts can access multiple PCIe expansion modules (PCIe resource pools), that is, to realize PCIe resources. Sharing among multiple hosts.
进一步的,所述主机与PCIe设备解耦方法,还可以包括:根据所述数据处理器的带宽和所述PCIe交换机的带宽分别对所述数据处理器的数量和所述PCIe交换机的数量进行调节。可以理解的是,数据处理器的带宽越宽,所能处理的数据也就越多,对应的数据处理器的数量也越多,因此可以根据数据处理器的带宽调节数据处理器的数量。同理,可以根据PCIe交换机的带宽对PCIe交换机的数量进行调节。Further, the method for decoupling the host from the PCIe device may further include: respectively adjusting the number of the data processors and the number of the PCIe switches according to the bandwidth of the data processor and the bandwidth of the PCIe switch . It can be understood that the wider the bandwidth of the data processor, the more data that can be processed, and the more the corresponding number of data processors, therefore, the number of data processors can be adjusted according to the bandwidth of the data processor. Similarly, the number of PCIe switches can be adjusted according to the bandwidth of the PCIe switches.
可见,本申请实施例先将PCIe扩展模块从主机中分离,得到独立PCIe扩展模块,然后在所述独立PCIe扩展模块中,将所述PCIe交换机与数据处理器相连,得到目标PCIe扩展模块,并通过所述数据处理器将所述目标PCIe扩展模块接入到以太网,再通过内接的OCP网卡将所述主机接入到所述以太网,并通过以太网矩阵实现所述目标PCIe扩展模块与所述主机的通信。本申请实施例在PCIe扩展模块中,添加与PCIe交换机相连的数据处理器,然后通过数据处理器将PCIe协议转换成以太网协议,并通过以太网矩阵实现解耦后的PCIe扩展模块与主机的通信和资源共享,能够降低主机的设计难度,便于主板和PCIe设备的扩展和独立升级,并使扩展性最大化,可快速向市场推出,应用灵活。It can be seen that in the embodiment of the present application, the PCIe expansion module is first separated from the host to obtain an independent PCIe expansion module, and then in the independent PCIe expansion module, the PCIe switch is connected with the data processor to obtain the target PCIe expansion module, and The target PCIe expansion module is connected to the Ethernet through the data processor, then the host is connected to the Ethernet through the built-in OCP network card, and the target PCIe expansion module is implemented through the Ethernet matrix communication with the host. In this embodiment of the present application, a data processor connected to a PCIe switch is added to the PCIe expansion module, and then the PCIe protocol is converted into an Ethernet protocol through the data processor, and the decoupled PCIe expansion module and the host are realized through the Ethernet matrix. Communication and resource sharing can reduce the design difficulty of the host, facilitate the expansion and independent upgrade of motherboards and PCIe devices, maximize the scalability, and can be quickly introduced to the market with flexible applications.
参见图3所示,图3示出了一种具体的主机与PCIe设备解耦后的PCIe扩展模块拓扑结构图,其中,解耦后的主机包括中央处理器、根复合体和OCP网卡,并且中央处理器与根复合体直接连接,根复合体可以和多个OCP网卡相连;解耦后的PCIe扩展模块(即独立PCIe扩展模块)包括数据处理器、PCIe交换机和相连的多个PCIe终端设备,其中,数据处理器通过对内的端口与PCIe交换机直接相连,通过对外的网口可以与主机进行连接,具体可通过以太网矩阵实现解耦后的主机和解耦后的PCIe扩展模块的连接。在一种具体的实施方式中,参见图4所示,图4示出了一种具体的解耦后的PCIe扩展模块的硬件结构示意图,该模块由多个PCIe连接器插槽、PCIe印刷电路板、目标芯片(包括PCIe交换机芯片、数据处理器芯片、基板管理控制器芯片)以及冷板四个部分组成。模块采用紧凑的堆叠结构,将散热、电源等器件与PCIe资源集成在更小的体积内,最大化利用空间,实现小型化的模块构造。图4中在PCIe印刷电路板的正面放置了10个PCIe连接器插槽,是PCIe资源扩展的下游端口,可以连接10个×16插槽的PCIe终端设备,或者更多的×2插槽、×4插槽以及×8插槽的PCIe终端设备。另外,在PCIe印刷电路板的正面还放置了两个由数据处理器接出的网口,用于实现解耦后的PCIe扩展模块与主机的互联与通信。PCIe交换机芯片、数据处理器芯片以及基板管理控制器芯片放置在PCIe印刷电路板的背面,PCIe交换机芯片用于扩展PCIe的下游端口,数据处理器芯片提供PCIe根复合体(即上游端口),能够实现PCIe协议转以太网协议,而基板管理控制器芯片则可以用于PCIe设备的管理。通过在PCIe印刷电路板中走线,可以实现和PCIe的上游端口、下游端口之间的连接以及对下游端口的管理。PCIe印刷电路板的背面是一块采用液冷方式的冷板,用于对目标芯片及PCIe设备进行散热与供电(电源可集成在冷板背面)。为达到最优的散热效果,冷板和PCIe印刷电路板可以紧贴在一起。进一步的,采用多个独立PCIe扩展模块还可以实现PCIe资源的池化。具体的,将所有的PCIe设备均通过PCIe交换机、数据处理器接入到以太网中,在以太网中可以实现多个独立PCIe扩展模块之间以及多个独立PCIe扩展模块与主机之间的互联与通信,为主机提供最大化的资源扩展。另外,如果增加网口数量,独立PCIe扩展模块还可以接到多个主机上,从而实现多个主机访问PCIe资源池,即实现了PCIe资源在多个主机之间的共享。Referring to FIG. 3, FIG. 3 shows a specific topology diagram of a PCIe expansion module after the host is decoupled from the PCIe device, wherein the decoupled host includes a central processing unit, a root complex, and an OCP network card, and The central processing unit is directly connected to the root complex, and the root complex can be connected to multiple OCP network cards; the decoupled PCIe expansion module (ie, independent PCIe expansion module) includes a data processor, a PCIe switch, and multiple connected PCIe terminal devices , wherein the data processor is directly connected to the PCIe switch through the internal port, and can be connected to the host through the external network port. Specifically, the connection between the decoupled host and the decoupled PCIe expansion module can be realized through the Ethernet matrix. . In a specific implementation, referring to FIG. 4 , FIG. 4 shows a schematic diagram of the hardware structure of a specific decoupled PCIe expansion module. The module consists of a plurality of PCIe connector slots, a PCIe printed circuit It consists of four parts: board, target chip (including PCIe switch chip, data processor chip, baseboard management controller chip) and cold plate. The module adopts a compact stack structure, which integrates components such as heat dissipation, power supply, and PCIe resources into a smaller volume, maximizes the use of space, and realizes a miniaturized module structure. In Figure 4, 10 PCIe connector slots are placed on the front of the PCIe printed circuit board, which are downstream ports for PCIe resource expansion, which can connect 10 × 16 slots of PCIe terminal devices, or more × 2 slots, PCIe terminal devices with ×4 slots and ×8 slots. In addition, two network ports connected by the data processor are placed on the front of the PCIe printed circuit board to realize interconnection and communication between the decoupled PCIe expansion module and the host. The PCIe switch chip, data processor chip, and baseboard management controller chip are placed on the back of the PCIe printed circuit board. The PCIe switch chip is used to expand the downstream ports of PCIe. The data processor chip provides the PCIe root complex (ie, the upstream port), which can The PCIe protocol is converted to the Ethernet protocol, and the baseboard management controller chip can be used for PCIe device management. By routing wires in the PCIe printed circuit board, the connection with the upstream port of the PCIe, the connection between the downstream port and the management of the downstream port can be realized. The back of the PCIe printed circuit board is a liquid-cooled cold plate, which is used to dissipate heat and supply power to the target chip and PCIe devices (the power supply can be integrated on the back of the cold plate). For optimal heat dissipation, the cold plate and PCIe printed circuit board can be placed close together. Further, using multiple independent PCIe expansion modules can also realize the pooling of PCIe resources. Specifically, all PCIe devices are connected to the Ethernet through PCIe switches and data processors, and the interconnection between multiple independent PCIe expansion modules and between multiple independent PCIe expansion modules and the host can be realized in the Ethernet. Communicate with to provide maximum resource expansion for the host. In addition, if the number of network ports is increased, the independent PCIe expansion module can also be connected to multiple hosts, so that multiple hosts can access the PCIe resource pool, that is, the sharing of PCIe resources among multiple hosts is realized.
由上可见,本申请的技术方案通过将PCIe设备从主机设计中解耦出来,并将PCIe资源池化,这种独立的扩展模块符合当今的模块化和资源池化的趋势,降低了主机的设计难度,便于主机和PCIe资源的各自扩展和独立更新换代,可快速向市场推出,应用灵活。通过以太网实现独立PCIe扩展模块与主机的连接,便于多台主机对PCIe资源池的访问,实现了资源共享。并且采用堆叠结构,将PCIe设备与散热、电源等器件叠放在一起,形成独立的小型PCIe扩展模块,可在一个机箱中放置多个独立PCIe扩展模块,进而将可扩展性最大化。It can be seen from the above that the technical solution of the present application decouples the PCIe device from the host design and pools the PCIe resources. This independent expansion module conforms to the current trend of modularization and resource pooling, and reduces the host's cost. The design is difficult, and it is convenient for the respective expansion and independent replacement of the host and PCIe resources, which can be quickly introduced to the market and have flexible applications. The connection between the independent PCIe expansion module and the host is realized through Ethernet, which facilitates the access of multiple hosts to the PCIe resource pool and realizes resource sharing. In addition, the stacking structure is adopted, and PCIe devices are stacked with heat dissipation, power supply and other devices to form an independent small PCIe expansion module. Multiple independent PCIe expansion modules can be placed in one chassis, thereby maximizing scalability.
相应的,本申请实施例还公开了一种主机与PCIe设备解耦装置,参见图5所示,该装置包括:Correspondingly, an embodiment of the present application also discloses an apparatus for decoupling a host from a PCIe device. Referring to FIG. 5 , the apparatus includes:
分离模块11,用于将PCIe扩展模块从主机中分离,得到独立PCIe扩展模块;所述独立PCIe扩展模块包括PCIe交换机和多个通过PCIe连接器与所述PCIe交换机相连的PCIe终端设备;The
连接模块12,用于在所述独立PCIe扩展模块中,将所述PCIe交换机与数据处理器相连,得到目标PCIe扩展模块,并通过所述数据处理器将所述目标PCIe扩展模块接入到以太网;The
通信模块13,用于通过内接的OCP网卡将所述主机接入到所述以太网,并通过以太网矩阵实现所述目标PCIe扩展模块与所述主机的通信。The
其中,关于上述各个模块的具体工作流程可以参考前述实施例中公开的相应内容,在此不再进行赘述。For the specific work flow of the above modules, reference may be made to the corresponding content disclosed in the foregoing embodiments, which will not be repeated here.
可见,本申请实施例中,先将PCIe扩展模块从主机中分离,得到独立PCIe扩展模块,然后在所述独立PCIe扩展模块中,将所述PCIe交换机与数据处理器相连,得到目标PCIe扩展模块,并通过所述数据处理器将所述目标PCIe扩展模块接入到以太网,再通过内接的OCP网卡将所述主机接入到所述以太网,并通过以太网矩阵实现所述目标PCIe扩展模块与所述主机的通信。本申请实施例在PCIe扩展模块中,添加与PCIe交换机相连的数据处理器,然后通过数据处理器将PCIe协议转换成以太网协议,并通过以太网矩阵实现解耦后的PCIe扩展模块与主机的通信和资源共享,能够降低主机的设计难度,便于主板和PCIe设备的扩展和独立升级,并使扩展性最大化,可快速向市场推出,应用灵活。It can be seen that in the embodiment of the present application, the PCIe expansion module is first separated from the host to obtain an independent PCIe expansion module, and then in the independent PCIe expansion module, the PCIe switch is connected with the data processor to obtain the target PCIe expansion module , and connect the target PCIe expansion module to the Ethernet through the data processor, then connect the host to the Ethernet through the built-in OCP network card, and realize the target PCIe through the Ethernet matrix Communication between expansion modules and the host. In this embodiment of the present application, a data processor connected to a PCIe switch is added to the PCIe expansion module, and then the PCIe protocol is converted into an Ethernet protocol through the data processor, and the decoupled PCIe expansion module and the host are realized through the Ethernet matrix. Communication and resource sharing can reduce the design difficulty of the host, facilitate the expansion and independent upgrade of motherboards and PCIe devices, maximize the scalability, and can be quickly introduced to the market with flexible applications.
在一些具体实施例中,所述连接模块12,具体可以包括:In some specific embodiments, the
以太网接入单元,用于通过所述数据处理器对外提供的网口将所述目标PCIe扩展模块中的所述PCIe交换机、所述PCIe连接器和所述PCIe交换机接入到以太网。An Ethernet access unit, configured to connect the PCIe switch, the PCIe connector and the PCIe switch in the target PCIe expansion module to the Ethernet through a network port provided by the data processor.
在一些具体实施例中,所述主机与PCIe设备解耦装置,还可以包括:In some specific embodiments, the apparatus for decoupling the host from the PCIe device may further include:
数量调节单元,用于根据所述数据处理器的带宽和所述PCIe交换机的带宽分别对所述数据处理器的数量和所述PCIe交换机的数量进行调节。A quantity adjustment unit, configured to adjust the quantity of the data processors and the quantity of the PCIe switches respectively according to the bandwidth of the data processors and the bandwidth of the PCIe switches.
在一些具体实施例中,所述目标PCIe扩展模块的硬件结构由多个PCIe连接器插槽、PCIe印刷电路板、目标芯片和冷板组成;其中,所述目标芯片包括PCIe交换机芯片、数据处理器芯片和管理芯片。In some specific embodiments, the hardware structure of the target PCIe expansion module is composed of a plurality of PCIe connector slots, a PCIe printed circuit board, a target chip and a cold plate; wherein the target chip includes a PCIe switch chip, a data processing device chip and management chip.
在一些具体实施例中,所述多个PCIe连接器插槽和所述目标芯片位于所述PCIe印刷电路板的正面,所述冷板位于所述PCIe印刷电路板的背面。In some specific embodiments, the plurality of PCIe connector slots and the target chip are located on the front side of the PCIe printed circuit board, and the cold plate is located on the back side of the PCIe printed circuit board.
在一些具体实施例中,所述主机与PCIe设备解耦装置,还可以包括:In some specific embodiments, the apparatus for decoupling the host from the PCIe device may further include:
集成单元,用于采用紧凑的堆叠结构将所述多个PCIe连接器插槽、所述目标芯片、所述冷板、电源和散热器集成在所述PCIe印刷电路板上。An integration unit for integrating the plurality of PCIe connector slots, the target chip, the cold plate, the power supply and the heat sink on the PCIe printed circuit board in a compact stack structure.
在一些具体实施例中,所述主机与PCIe设备解耦装置,还可以包括:In some specific embodiments, the apparatus for decoupling the host from the PCIe device may further include:
互联与通信单元,用于获取多个所述目标PCIe扩展模块,并通过所述以太网实现多个所述目标PCIe扩展模块之间及多个所述目标PCIe扩展模块与所述主机之间的互联与通信。The interconnection and communication unit is used to obtain a plurality of the target PCIe expansion modules, and realize the communication between the multiple target PCIe expansion modules and between the multiple target PCIe expansion modules and the host through the Ethernet. interconnection and communication.
进一步的,本申请实施例还公开了一种电子设备,图6是根据一示例性实施例示出的电子设备20结构图,图中的内容不能认为是对本申请的使用范围的任何限制。Further, an embodiment of the present application also discloses an electronic device. FIG. 6 is a structural diagram of an
图6为本申请实施例提供的一种电子设备20的结构示意图。该电子设备20,具体可以包括:至少一个处理器21、至少一个存储器22、电源23、通信接口24、输入输出接口25和通信总线26。其中,所述存储器22用于存储计算机程序,所述计算机程序由所述处理器21加载并执行,以实现前述任一实施例公开的主机与PCIe设备解耦方法中的相关步骤。另外,本实施例中的电子设备20具体可以为电子计算机。FIG. 6 is a schematic structural diagram of an
本实施例中,电源23用于为电子设备20上的各硬件设备提供工作电压;通信接口24能够为电子设备20创建与外界设备之间的数据传输通道,其所遵循的通信协议是能够适用于本申请技术方案的任意通信协议,在此不对其进行具体限定;输入输出接口25,用于获取外界输入数据或向外界输出数据,其具体的接口类型可以根据具体应用需要进行选取,在此不进行具体限定。In this embodiment, the power supply 23 is used to provide working voltage for each hardware device on the
另外,存储器22作为资源存储的载体,可以是只读存储器、随机存储器、磁盘或者光盘等,其上所存储的资源可以包括操作系统221、计算机程序222等,存储方式可以是短暂存储或者永久存储。In addition, as a carrier for resource storage, the memory 22 can be a read-only memory, a random access memory, a magnetic disk or an optical disk, etc. The resources stored on it can include an operating system 221, a computer program 222, etc., and the storage method can be short-term storage or permanent storage. .
其中,操作系统221用于管理与控制电子设备20上的各硬件设备以及计算机程序222,其可以是Windows Server、Netware、Unix、Linux等。计算机程序222除了包括能够用于完成前述任一实施例公开的由电子设备20执行的主机与PCIe设备解耦方法的计算机程序之外,还可以进一步包括能够用于完成其他特定工作的计算机程序。The operating system 221 is used to manage and control various hardware devices and computer programs 222 on the
进一步的,本申请还公开了一种计算机可读存储介质,用于存储计算机程序;其中,所述计算机程序被处理器执行时实现前述公开的主机与PCIe设备解耦方法。关于该方法的具体步骤可以参考前述实施例中公开的相应内容,在此不再进行赘述。Further, the present application also discloses a computer-readable storage medium for storing a computer program; wherein, when the computer program is executed by a processor, the aforementioned method for decoupling a host and a PCIe device is implemented. For the specific steps of the method, reference may be made to the corresponding content disclosed in the foregoing embodiments, which will not be repeated here.
本说明书中各个实施例采用递进的方式描述,每个实施例重点说明的都是与其它实施例的不同之处,各个实施例之间相同或相似部分互相参见即可。对于实施例公开的装置而言,由于其与实施例公开的方法相对应,所以描述的比较简单,相关之处参见方法部分说明即可。The various embodiments in this specification are described in a progressive manner, and each embodiment focuses on the differences from other embodiments, and the same or similar parts between the various embodiments may be referred to each other. As for the device disclosed in the embodiment, since it corresponds to the method disclosed in the embodiment, the description is relatively simple, and the relevant part can be referred to the description of the method.
专业人员还可以进一步意识到,结合本文中所公开的实施例描述的各示例的单元及算法步骤,能够以电子硬件、计算机软件或者二者的结合来实现,为了清楚地说明硬件和软件的可互换性,在上述说明中已经按照功能一般性地描述了各示例的组成及步骤。这些功能究竟以硬件还是软件方式来执行,取决于技术方案的特定应用和设计约束条件。专业技术人员可以对每个特定的应用来使用不同方法来实现所描述的功能,但是这种实现不应认为超出本申请的范围。Professionals may further realize that the units and algorithm steps of each example described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, computer software, or a combination of the two, in order to clearly illustrate the possibilities of hardware and software. Interchangeability, the above description has generally described the components and steps of each example in terms of functionality. Whether these functions are performed in hardware or software depends on the specific application and design constraints of the technical solution. Skilled artisans may implement the described functionality using different methods for each particular application, but such implementations should not be considered beyond the scope of this application.
结合本文中所公开的实施例描述的方法或算法的步骤可以直接用硬件、处理器执行的软件模块,或者二者的结合来实施。软件模块可以置于随机存储器(RAM)、内存、只读存储器(ROM)、电可编程ROM、电可擦除可编程ROM、寄存器、硬盘、可移动磁盘、CD-ROM、或技术领域内所公知的任意其它形式的存储介质中。The steps of a method or algorithm described in conjunction with the embodiments disclosed herein may be directly implemented in hardware, a software module executed by a processor, or a combination of the two. A software module can be placed in random access memory (RAM), internal memory, read only memory (ROM), electrically programmable ROM, electrically erasable programmable ROM, registers, hard disk, removable disk, CD-ROM, or any other in the technical field. in any other known form of storage medium.
最后,还需要说明的是,在本文中,诸如第一和第二等之类的关系术语仅仅用来将一个实体或者操作与另一个实体或操作区分开来,而不一定要求或者暗示这些实体或操作之间存在任何这种实际的关系或者顺序。而且,术语“包括”、“包含”或者其任何其他变体意在涵盖非排他性的包含,从而使得包括一系列要素的过程、方法、物品或者设备不仅包括那些要素,而且还包括没有明确列出的其他要素,或者是还包括为这种过程、方法、物品或者设备所固有的要素。在没有更多限制的情况下,由语句“包括一个……”限定的要素,并不排除在包括所述要素的过程、方法、物品或者设备中还存在另外的相同要素。Finally, it should also be noted that in this document, relational terms such as first and second are used only to distinguish one entity or operation from another, and do not necessarily require or imply these entities or that there is any such actual relationship or sequence between operations. Moreover, the terms "comprising", "comprising" or any other variation thereof are intended to encompass non-exclusive inclusion such that a process, method, article or device comprising a list of elements includes not only those elements, but also includes not explicitly listed or other elements inherent to such a process, method, article or apparatus. Without further limitation, an element qualified by the phrase "comprising a..." does not preclude the presence of additional identical elements in a process, method, article or apparatus that includes the element.
以上对本申请所提供的一种主机与PCIe设备解耦方法、装置、设备及存储介质进行了详细介绍,本文中应用了具体个例对本申请的原理及实施方式进行了阐述,以上实施例的说明只是用于帮助理解本申请的方法及其核心思想;同时,对于本领域的一般技术人员,依据本申请的思想,在具体实施方式及应用范围上均会有改变之处,综上所述,本说明书内容不应理解为对本申请的限制。A method, device, device, and storage medium for decoupling a host from a PCIe device provided by the present application have been described in detail above. The principles and implementations of the present application are described with specific examples in this article. It is only used to help understand the method of the present application and its core idea; at the same time, for those of ordinary skill in the art, according to the idea of the present application, there will be changes in the specific embodiments and application scope. In summary, The contents of this specification should not be construed as limiting the application.
Claims (10)
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210465823.6A CN114780472A (en) | 2022-04-29 | 2022-04-29 | Host and PCIe device decoupling method, device, equipment and storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210465823.6A CN114780472A (en) | 2022-04-29 | 2022-04-29 | Host and PCIe device decoupling method, device, equipment and storage medium |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN114780472A true CN114780472A (en) | 2022-07-22 |
Family
ID=82434889
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202210465823.6A Withdrawn CN114780472A (en) | 2022-04-29 | 2022-04-29 | Host and PCIe device decoupling method, device, equipment and storage medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN114780472A (en) |
Cited By (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN115442239A (en) * | 2022-08-01 | 2022-12-06 | 超聚变数字技术有限公司 | Bandwidth resource allocation method, PCIe channel switcher and electronic equipment |
| CN115733549A (en) * | 2023-01-10 | 2023-03-03 | 苏州浪潮智能科技有限公司 | PCIE network card and its interface mode switching method, electronic equipment and storage medium |
| CN116069709A (en) * | 2023-01-06 | 2023-05-05 | 超聚变数字技术有限公司 | Server system and network card integration equipment |
| CN117041184A (en) * | 2023-10-10 | 2023-11-10 | 苏州元脑智能科技有限公司 | IO expansion architecture, IO switch and PCIe device |
| CN117033287A (en) * | 2023-10-08 | 2023-11-10 | 易方信息科技股份有限公司 | Multi-bus communication method, system, equipment and storage medium based on SDK (software development kit) package |
| CN117851304A (en) * | 2024-03-07 | 2024-04-09 | 济南浪潮数据技术有限公司 | A hard disk replacement method, device, equipment and medium |
| WO2024212744A1 (en) * | 2023-04-14 | 2024-10-17 | 广东浪潮智慧计算技术有限公司 | Server, heterogeneous device, and data processing apparatus thereof |
-
2022
- 2022-04-29 CN CN202210465823.6A patent/CN114780472A/en not_active Withdrawn
Cited By (11)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN115442239A (en) * | 2022-08-01 | 2022-12-06 | 超聚变数字技术有限公司 | Bandwidth resource allocation method, PCIe channel switcher and electronic equipment |
| CN115442239B (en) * | 2022-08-01 | 2024-02-09 | 河南昆仑技术有限公司 | Bandwidth resource allocation method, PCIe channel switcher and electronic device |
| CN116069709A (en) * | 2023-01-06 | 2023-05-05 | 超聚变数字技术有限公司 | Server system and network card integration equipment |
| CN115733549A (en) * | 2023-01-10 | 2023-03-03 | 苏州浪潮智能科技有限公司 | PCIE network card and its interface mode switching method, electronic equipment and storage medium |
| CN115733549B (en) * | 2023-01-10 | 2023-04-28 | 苏州浪潮智能科技有限公司 | PCIE network card, switching method of interface modes of PCIE network card, electronic equipment and storage medium |
| WO2024212744A1 (en) * | 2023-04-14 | 2024-10-17 | 广东浪潮智慧计算技术有限公司 | Server, heterogeneous device, and data processing apparatus thereof |
| CN117033287A (en) * | 2023-10-08 | 2023-11-10 | 易方信息科技股份有限公司 | Multi-bus communication method, system, equipment and storage medium based on SDK (software development kit) package |
| CN117033287B (en) * | 2023-10-08 | 2024-02-13 | 易方信息科技股份有限公司 | Multi-bus communication method, system, equipment and storage medium based on SDK (software development kit) package |
| CN117041184A (en) * | 2023-10-10 | 2023-11-10 | 苏州元脑智能科技有限公司 | IO expansion architecture, IO switch and PCIe device |
| CN117041184B (en) * | 2023-10-10 | 2024-02-09 | 苏州元脑智能科技有限公司 | IO expansion device and IO switch |
| CN117851304A (en) * | 2024-03-07 | 2024-04-09 | 济南浪潮数据技术有限公司 | A hard disk replacement method, device, equipment and medium |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN114780472A (en) | Host and PCIe device decoupling method, device, equipment and storage medium | |
| US20260010503A1 (en) | Support for multiple hot pluggable devices via emulated switch | |
| CN106126448B (en) | Storage system | |
| CN116069709A (en) | Server system and network card integration equipment | |
| CN106155959A (en) | Data transmission method and data transmission system | |
| CN113645047A (en) | Out-of-band management system and server based on intelligent network card | |
| CN111581050B (en) | Cabinet, cabinet monitoring system and monitoring method | |
| US11011876B2 (en) | System and method for remote management of network interface peripherals | |
| US20050021654A1 (en) | Simultaneous sharing of storage drives on blade center | |
| CN103793003B (en) | A kind of power board and blade server | |
| CN102611560A (en) | Interlayer card, server and server system | |
| CN119356490A (en) | Mainboard, mainboard system, server, node interconnection structure and server system | |
| CN104820474A (en) | Cloud server mainboard, cloud server and realization method thereof | |
| WO2025077411A1 (en) | Io expansion architecture, io switch and pcie device | |
| US7188205B2 (en) | Mapping of hot-swap states to plug-in unit states | |
| CN101924682A (en) | An advanced telecommunications computing architecture switching system, method and communication equipment | |
| CN118885422A (en) | Server and backplane | |
| US12007928B2 (en) | Signal bridging using an unpopulated processor interconnect | |
| CN111897754B (en) | External multi-host system | |
| CN103984390B (en) | Blade and blade server | |
| US8151011B2 (en) | Input-output fabric conflict detection and resolution in a blade compute module system | |
| US6977925B2 (en) | Folded fabric switching architecture | |
| CN214959602U (en) | BCM 56980-based ultra-large bandwidth core switching equipment | |
| CN112732627B (en) | OCP device and server | |
| CN115145856A (en) | An OCP network card system |
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 | ||
| WW01 | Invention patent application withdrawn after publication | ||
| WW01 | Invention patent application withdrawn after publication |
Application publication date: 20220722 |
