CN112597094B - Device and method for improving RDMA transmission efficiency - Google Patents
Device and method for improving RDMA transmission efficiency Download PDFInfo
- Publication number
- CN112597094B CN112597094B CN202011543181.4A CN202011543181A CN112597094B CN 112597094 B CN112597094 B CN 112597094B CN 202011543181 A CN202011543181 A CN 202011543181A CN 112597094 B CN112597094 B CN 112597094B
- Authority
- CN
- China
- Prior art keywords
- server
- expansion board
- data
- memory
- memory expansion
- 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.)
- Active
Links
- 230000005540 biological transmission Effects 0.000 title claims abstract description 61
- 238000000034 method Methods 0.000 title claims abstract description 37
- 238000004590 computer program Methods 0.000 description 7
- 238000010586 diagram Methods 0.000 description 7
- 230000006870 function Effects 0.000 description 5
- 230000008569 process Effects 0.000 description 5
- 230000005577 local transmission Effects 0.000 description 3
- 230000000694 effects Effects 0.000 description 2
- 238000012986 modification Methods 0.000 description 2
- 230000004048 modification Effects 0.000 description 2
- 230000004075 alteration Effects 0.000 description 1
- 238000004519 manufacturing process Methods 0.000 description 1
- 230000003287 optical effect Effects 0.000 description 1
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F15/00—Digital computers in general; Data processing equipment in general
- G06F15/16—Combinations of two or more digital computers each having at least an arithmetic unit, a program unit and a register, e.g. for a simultaneous processing of several programs
- G06F15/163—Interprocessor communication
- G06F15/173—Interprocessor communication using an interconnection network, e.g. matrix, shuffle, pyramid, star, snowflake
- G06F15/17306—Intercommunication techniques
- G06F15/17331—Distributed shared memory [DSM], e.g. remote direct memory access [RDMA]
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F13/00—Interconnection of, or transfer of information or other signals between, memories, input/output devices or central processing units
- G06F13/38—Information transfer, e.g. on bus
- G06F13/40—Bus structure
- G06F13/4004—Coupling between buses
- G06F13/4027—Coupling between buses using bus bridges
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
- H04L67/00—Network arrangements or protocols for supporting network services or applications
- H04L67/01—Protocols
- H04L67/10—Protocols in which an application is distributed across nodes in the network
- H04L67/1095—Replication or mirroring of data, e.g. scheduling or transport for data synchronisation between network nodes
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR 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)
- Theoretical Computer Science (AREA)
- Computer Hardware Design (AREA)
- General Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Computer Networks & Wireless Communication (AREA)
- Signal Processing (AREA)
- Mathematical Physics (AREA)
- Software Systems (AREA)
- Bus Control (AREA)
Abstract
The invention provides a device and a method for improving RDMA transmission efficiency, wherein the device comprises the following components: a first server; the second server is arranged in parallel with the first server; the memory expansion board is provided with a PCIe bridging chip; the memory expansion board is connected with the first server and the second server through the PCIe bridge chip. Through increasing PCIe bridging chip on the memory expansion board, the CXL protocol-based direct reading of data from the memory expansion board is realized, the data transmission process between network cards is omitted, the local data transmission is realized, the transmission speed is faster, and the safety is higher.
Description
Technical Field
The invention relates to the technical field of RDMA transmission efficiency, in particular to a device and a method for improving RDMA transmission efficiency.
Background
The conventional RDMA technology for data transmission at the current server side, namely, remote memory direct reading is adopted, so that application programs are allowed to directly perform data transmission between the memory spaces of the application programs, the intervention of a kernel and a CPU is not needed, and compared with the conventional mode, the RDMA technology saves system resources and improves transmission efficiency.
However, in the process of implementing the technical solution in the embodiment of the present application, the present inventors have found that at least the following technical problems exist in the prior art:
In the prior art, RDMA technology is adopted to carry out data transmission of a server side, so that the technical problems of more occupied system resources, low transmission efficiency and low safety exist.
Disclosure of Invention
The embodiment of the invention provides a device and a method for improving RDMA transmission efficiency, which are used for solving the technical problems that the prior art adopts RDMA technology to carry out data transmission of a server side, and the invention occupies more system resources, has low transmission efficiency and has low safety. Through increasing PCIe bridging chip on the memory expansion board, the CXL protocol-based direct reading of data from the memory expansion board is realized, the data transmission process between network cards is omitted, the local data transmission is realized, the transmission speed is faster, and the safety is higher.
In view of the foregoing, embodiments of the present application are presented to provide an apparatus and method for improving RDMA transmission efficiency.
In a first aspect, the present invention provides an apparatus for improving RDMA transmission efficiency, the apparatus comprising: a first server; the second server is arranged in parallel with the first server; the memory expansion board is provided with a PCIe bridging chip; the memory expansion board is connected with the first server and the second server through the PCIe bridge chip.
Preferably, the first server further includes: the first main memory is positioned on the first server and is used for processing the data on the first server; and the first PCIe device is connected with the first main memory and is used for transmitting the data processed by the first main memory to the memory expansion board through a PCIe protocol.
Preferably, the second server further includes: the second main memory is positioned on the second server and is used for processing the data on the second server; and the second PCIe device is connected with the second main memory and is used for transmitting the data processed by the second main memory to the memory expansion board through a PCIe protocol.
In a second aspect, the present invention provides a method of improving RDMA transmission efficiency, the method comprising: obtaining a memory expansion board; adding the PCIe bridge chip on the memory expansion board; the method comprises the steps of obtaining a first server and a second server of data to be transmitted mutually; connecting the first server with the memory expansion board through the PCIe bridge chip; connecting the second server with the memory expansion board through the PCIe bridge chip; the first server directly stores the processed data to the memory expansion board; and the second server directly reads the data stored by the first server from the memory expansion board.
Preferably, the method further comprises: the second server directly stores the processed data to the memory expansion board; and the first server directly reads the data stored by the second server from the memory expansion board.
Preferably, the first server directly stores the processed data onto the memory expansion board, including: processing data by the first main memory on the first server; and the first main memory directly stores the processed data to the memory expansion board through the first PCIe device.
Preferably, the second server directly reads the data stored by the first server from the memory expansion board, including: the memory expansion board transmits the data stored by the first server to the second PCIe device through CXL protocol; the second PCIe device transmits the received data to the second host.
Preferably, the second server directly stores the processed data onto the memory expansion board, including: processing the data by the second main memory on the second server; and the second main memory directly stores the processed data to the memory expansion board through second PCIe equipment.
Preferably, the first server directly reads the data stored by the second server from the memory expansion board, including: the memory expansion board transmits the data stored by the second server to the first PCIe device through CXL protocol; the first PCIe device transmits the received data to the first host.
The above technical solutions in the embodiments of the present application at least have one or more of the following technical effects:
The embodiment of the invention provides a device and a method for improving RDMA transmission efficiency, wherein the device comprises the following steps: a first server; the second server is arranged in parallel with the first server; the memory expansion board is provided with a PCIe bridging chip; the memory expansion board is connected with the first server and the second server through the PCIe bridge chip. The RDMA data transmission method is used for solving the technical problems that in the prior art, RDMA technology is adopted for data transmission of a server side, system resources are occupied, transmission efficiency is low, and safety is low. Through increasing PCIe bridging chip on the memory expansion board, the CXL protocol-based direct reading of data from the memory expansion board is realized, the data transmission process between network cards is omitted, the local data transmission is realized, the transmission speed is faster, and the safety is higher.
The foregoing description is only an overview of the present invention, and is intended to be implemented in accordance with the teachings of the present invention in order that the same may be more clearly understood and to make the same and other objects, features and advantages of the present invention more readily apparent.
Drawings
FIG. 1 is a schematic diagram of an apparatus for improving RDMA transmission efficiency according to an embodiment of the present invention;
fig. 2 is a flowchart illustrating a method for improving RDMA transmission efficiency according to an embodiment of the present invention.
Reference numerals illustrate: the memory comprises a first main memory 1, a first PCIe device 2, a second main memory 3, a second PCIe device 4, a memory expansion board 5 and a PCIe bridge chip 6.
Detailed Description
The embodiment of the invention provides a device and a method for improving RDMA transmission efficiency, which are used for solving the technical problems that the prior art adopts RDMA technology to carry out data transmission of a server side, and the invention occupies more system resources, has low transmission efficiency and has low safety.
The technical scheme provided by the invention has the following overall thought: a first server; the second server is arranged in parallel with the first server; the memory expansion board is provided with a PCIe bridging chip; the memory expansion board is connected with the first server and the second server through the PCIe bridge chip. Through increasing PCIe bridging chip on the memory expansion board, the CXL protocol-based direct reading of data from the memory expansion board is realized, the data transmission process between network cards is omitted, the local data transmission is realized, the transmission speed is faster, and the safety is higher.
The following detailed description of the technical solutions of the present application will be given by way of the accompanying drawings and specific embodiments, and it should be understood that the specific features of the embodiments and embodiments of the present application are detailed descriptions of the technical solutions of the present application, and not limiting the technical solutions of the present application, and that the embodiments and technical features of the embodiments of the present application may be combined with each other without conflict.
The term "and/or" is herein merely an association relationship describing an associated object, meaning that there may be three relationships, e.g., a and/or B, may represent: a exists alone, A and B exist together, and B exists alone. In addition, the character "/" herein generally indicates that the front and rear associated objects are an "or" relationship.
Example 1
An embodiment of the present invention provides an apparatus for improving RDMA transmission efficiency, as shown in fig. 1, where the apparatus includes:
A first server;
the second server is arranged in parallel with the first server;
the memory expansion board 5, wherein a PCIe bridge chip 6 is arranged on the memory expansion board 5;
the memory expansion board 5 is connected with the first server and the second server through the PCIe bridge chip 6.
Further, the first server further includes: the first main memory 1 is positioned on the first server and is used for processing data on the first server; and the first PCIe device 2 connected to the first main memory 1 is configured to transmit the data processed by the first main memory 1 to the memory expansion board 5 through a PCIe protocol.
Further, the second server further includes: a second main memory 3 located on the second server, for processing data on the second server; and the second PCIe device 4 connected to the second main memory 3 is configured to transmit the data processed by the second main memory 3 to the memory expansion board 5 through a PCIe protocol.
In particular, RDMA is an abbreviation of english Remote Direct Memory Access, translated into remote direct data access, which is generated to solve the delay of server-side data processing in network transmission. RDMA transfers data directly into the memory area of a computer over a network, and moves the data quickly from one system to a remote system memory without any impact on the operating system, thus eliminating the need for more or less computer processing functions. It eliminates the overhead of external memory copying and context switching, thus freeing up memory bandwidth and CPU cycles for improved application system performance. In order to achieve higher data transmission rate at the server side, the embodiment of the application sets the PCIe bridge chip 6 on the external memory expansion board 5 of the system, and interconnects the first server and the second server through the PCIe bridge chip 6, where the PCIe bridge chip 6 can interconnect two or more servers, not only two servers, but also the memory expansion board 5 cooperates with Root Complex through cxl.mem and Flex Bus, so that conventional memory work can be replaced, that is, data called by PCIe devices (originally stored in conventional memory) can be stored in the memory on the memory expansion board 5, and normal work is not affected. For the first server, the first main memory 1 directly stores all the data stored on the network card on the memory chip on the memory expansion board 5 through the first PCIe device 2, and the second server omits a data transmission process from the network card to the network card when reading the data on the first server, and only needs to read the data from the memory expansion board 5 through the cxl.mem protocol, so that data transmission between multiple server ends is changed from network to local transmission, and the transmission speed is faster and the security is higher.
Example two
Fig. 2 is a flowchart illustrating a method for improving RDMA transmission efficiency according to an embodiment of the present invention. As shown in fig. 2, an embodiment of the present invention provides a method for improving RDMA transmission efficiency, where the method includes:
step s1: obtaining a memory expansion board 5;
Step s2: adding the PCIe bridge chip 6 on the memory expansion board 5;
Step s3: the method comprises the steps of obtaining a first server and a second server of data to be transmitted mutually;
step s4: connecting the first server with the memory expansion board 5 through the PCIe bridge chip 6;
Step s5: connecting the second server with the memory expansion board 5 through the PCIe bridge chip 6;
step s6: the first server directly stores the processed data to the memory expansion board 5;
step s7: the second server directly reads the data stored by the first server from the memory expansion board 5.
Further, the first server directly stores the processed data to the memory expansion board 5, including: the first main memory 1 on the first server processes data; the first main memory 1 directly stores the processed data to the memory expansion board 5 through the first PCIe device 2.
Further, the second server directly reads the data stored by the first server from the memory expansion board 5, including: the memory expansion board 5 transmits the data stored by the first server to the second PCIe device 4 through CXL protocol; the second PCIe device 4 transmits the received data to the second host 3.
Specifically, the memory expansion board 5 is externally connected to the system, the PCIe bridge chip 6 is disposed on the memory expansion board 5, and the first server and the second server are interconnected through the PCIe bridge chip 6, where the PCIe bridge chip 6 can interconnect two or more servers, not only limited to two servers, but the memory expansion board 5 cooperates with the Root Complex through cxl.mem and Flex Bus, and can replace conventional memory work, that is, data called by PCIe devices (originally stored in conventional memory) can be stored in the memory on the memory expansion board 5, so that normal operation is not affected. For the first server, the first main memory 1 directly stores all the data stored on the network card on the memory chip on the memory expansion board 5 through the first PCIe device 2, when the second server reads the data on the first server, a data transmission process from the network card to the network card is omitted, and only the data is required to be read from the memory expansion board 5 through the cxl.mem protocol, so that data transmission between multiple server ends is changed from network to local transmission, the transmission speed is faster, and the security is higher.
Further, the method further comprises: the second server directly stores the processed data to the memory expansion board 5; the first server directly reads the data stored by the second server from the memory expansion board 5.
Further, the second server directly stores the processed data to the memory expansion board 5, which includes: the second main memory 3 on the second server processes data; the second main memory 3 directly stores the processed data to the memory expansion board 5 through the second PCIe device 4.
Further, the first server directly reads the data stored by the second server from the memory expansion board 5, including: the memory expansion board 5 transmits the data stored by the second server to the first PCIe device 2 through CXL protocol; the first PCIe device 2 transmits the received data to the first host 1.
Specifically, the process of reading the data on the second server by the first server is the same as that described above, specifically, the second main memory 3 directly stores all the data stored on the network card on the memory chip on the memory expansion board 5 through the second PCIe device 4, when the first server reads the data on the second server, the data transmission process from the network card to the network card is omitted, and only the data is required to be read from the memory expansion board 5 through the cxl.mem protocol, so that data transmission between multiple server ends is changed from network to local transmission, the transmission speed is faster, and the security is higher.
The above technical solutions in the embodiments of the present application at least have one or more of the following technical effects:
The embodiment of the invention provides a device and a method for improving RDMA transmission efficiency, wherein the device comprises the following steps: a first server; the second server is arranged in parallel with the first server; the memory expansion board is provided with a PCIe bridging chip; the memory expansion board is connected with the first server and the second server through the PCIe bridge chip. The RDMA data transmission method is used for solving the technical problems that in the prior art, RDMA technology is adopted for data transmission of a server side, system resources are occupied, transmission efficiency is low, and safety is low. Through increasing PCIe bridging chip on the memory expansion board, the CXL protocol-based direct reading of data from the memory expansion board is realized, the data transmission process between network cards is omitted, the local data transmission is realized, the transmission speed is faster, and the safety is higher.
It will be appreciated by those skilled in the art that embodiments of the present invention may be provided as a method, system, or computer program product. Accordingly, the present invention may take the form of an entirely hardware embodiment, an entirely software embodiment or an embodiment combining software and hardware aspects. Furthermore, the present invention may take the form of a computer program product embodied on one or more computer-usable storage media (including, but not limited to, disk storage, CD-ROM, optical storage, and the like) having computer-usable program code embodied therein.
The present invention is described with reference to flowchart illustrations and/or block diagrams of methods, apparatus (systems) and computer program products according to embodiments of the invention. It will be understood that each flow and/or block of the flowchart illustrations and/or block diagrams, and combinations of flows and/or blocks in the flowchart illustrations and/or block diagrams, can be implemented by computer program instructions. These computer program instructions may be provided to a processor of a general purpose computer, special purpose computer, embedded processor, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, create means for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.
These computer program instructions may also be stored in a computer-readable memory that can direct a computer or other programmable data processing apparatus to function in a particular manner, such that the instructions stored in the computer-readable memory produce an article of manufacture including instruction means which implement the function specified in the flowchart flow or flows and/or block diagram block or blocks.
These computer program instructions may also be loaded onto a computer or other programmable data processing apparatus to cause a series of operational steps to be performed on the computer or other programmable apparatus to produce a computer implemented process such that the instructions which execute on the computer or other programmable apparatus provide steps for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.
It will be apparent to those skilled in the art that various modifications and variations can be made to the present invention without departing from the spirit or scope of the invention. Thus, it is intended that the present invention also include such modifications and alterations insofar as they come within the scope of the appended claims or the equivalents thereof.
Claims (7)
1. An apparatus for improving RDMA transmission efficiency, the apparatus comprising:
A first server;
the second server is arranged in parallel with the first server;
The memory expansion board is externally connected with the system, and a PCIe bridging chip is arranged on the memory expansion board;
The memory expansion board is connected with the first server and the second server through the PCIe bridging chip, so that the first server and the second server are interconnected, the memory expansion board cooperates with the Root Complex through CXL.mem and Flex Bus to replace the traditional memory operation, and data called by PCIe equipment is stored in a memory on the memory expansion board; wherein, the first server further includes:
The first main memory is positioned on the first server and is used for processing the data on the first server;
the first PCIe device is connected with the first main memory and is used for transmitting the data processed by the first main memory to the memory expansion board through a PCIe protocol;
wherein the second server further comprises:
the second main memory is positioned on the second server and is used for processing the data on the second server;
the second PCIe device is connected with the second main memory and is used for transmitting the data processed by the second main memory to the memory expansion board through a PCIe protocol;
And the first server and the second server are interconnected through the PCIe bridge chip, wherein the PCIe bridge chip can interconnect two or more servers, the first main memory directly stores all data stored on the network card on the memory chip on the memory expansion board through the first PCIe device, and the second server reads the data on the first server and reads the data from the memory expansion board through CXL.mem protocol.
2. A method for improving RDMA transmission efficiency, applied to an apparatus for improving RDMA transmission efficiency according to claim 1, the method comprising:
Obtaining a memory expansion board;
adding the PCIe bridge chip on the memory expansion board;
The method comprises the steps of obtaining a first server and a second server of data to be transmitted mutually;
connecting the first server with the memory expansion board through the PCIe bridge chip;
connecting the second server with the memory expansion board through the PCIe bridge chip;
the first server directly stores the processed data to the memory expansion board;
and the second server directly reads the data stored by the first server from the memory expansion board.
3. The method of claim 2, wherein the method further comprises:
the second server directly stores the processed data to the memory expansion board;
And the first server directly reads the data stored by the second server from the memory expansion board.
4. The method of claim 2, wherein the first server storing the processed data directly onto the memory expansion board comprises:
processing data by the first main memory on the first server;
And the first main memory directly stores the processed data to the memory expansion board through the first PCIe device.
5. The method of claim 2, wherein the second server directly reads the data stored by the first server from the memory expansion board, comprising:
The memory expansion board transmits the data stored by the first server to the second PCIe device through CXL protocol;
The second PCIe device transmits the received data to the second host.
6. The method of claim 3, wherein the second server directly stores the processed data onto the memory expansion board, comprising:
processing the data by the second main memory on the second server;
and the second main memory directly stores the processed data to the memory expansion board through second PCIe equipment.
7. The method of claim 3, wherein the first server reading the data stored by the second server directly from the memory expansion board comprises:
The memory expansion board transmits the data stored by the second server to the first PCIe device through CXL protocol;
the first PCIe device transmits the received data to the first host.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202011543181.4A CN112597094B (en) | 2020-12-24 | 2020-12-24 | Device and method for improving RDMA transmission efficiency |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202011543181.4A CN112597094B (en) | 2020-12-24 | 2020-12-24 | Device and method for improving RDMA transmission efficiency |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN112597094A CN112597094A (en) | 2021-04-02 |
| CN112597094B true CN112597094B (en) | 2024-05-31 |
Family
ID=75200871
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202011543181.4A Active CN112597094B (en) | 2020-12-24 | 2020-12-24 | Device and method for improving RDMA transmission efficiency |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN112597094B (en) |
Families Citing this family (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN116501681B (en) * | 2023-06-28 | 2023-09-29 | 苏州浪潮智能科技有限公司 | CXL data transmission board card and method for controlling data transmission |
Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN106933775A (en) * | 2013-10-29 | 2017-07-07 | 华为技术有限公司 | Data handling system and the method for data processing |
| CN109166074A (en) * | 2018-08-06 | 2019-01-08 | 联想(北京)有限公司 | computing system |
| CN109684256A (en) * | 2018-12-21 | 2019-04-26 | 联想(北京)有限公司 | Server and data transmission method |
| WO2020001459A1 (en) * | 2018-06-26 | 2020-01-02 | 华为技术有限公司 | Data processing method, remote direct memory access network card, and device |
| CN110825193A (en) * | 2019-12-24 | 2020-02-21 | 加弘科技咨询(上海)有限公司 | Method for connecting expansion card, adapter card module and server applied by adapter card module |
| CN210466253U (en) * | 2019-09-30 | 2020-05-05 | 广州超云科技有限公司 | Server with high-density GPU expansion capability |
Family Cites Families (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US9558148B2 (en) * | 2014-04-30 | 2017-01-31 | Intel Corporation | Method to optimize network data flows within a constrained system |
| CN106775434B (en) * | 2015-11-19 | 2019-11-29 | 华为技术有限公司 | A kind of implementation method, terminal, server and the system of NVMe networking storage |
| US10956336B2 (en) * | 2018-07-20 | 2021-03-23 | International Business Machines Corporation | Efficient silent data transmission between computer servers |
| US11748278B2 (en) * | 2019-06-20 | 2023-09-05 | Intel Corporation | Multi-protocol support for transactions |
-
2020
- 2020-12-24 CN CN202011543181.4A patent/CN112597094B/en active Active
Patent Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN106933775A (en) * | 2013-10-29 | 2017-07-07 | 华为技术有限公司 | Data handling system and the method for data processing |
| WO2020001459A1 (en) * | 2018-06-26 | 2020-01-02 | 华为技术有限公司 | Data processing method, remote direct memory access network card, and device |
| CN109166074A (en) * | 2018-08-06 | 2019-01-08 | 联想(北京)有限公司 | computing system |
| CN109684256A (en) * | 2018-12-21 | 2019-04-26 | 联想(北京)有限公司 | Server and data transmission method |
| CN210466253U (en) * | 2019-09-30 | 2020-05-05 | 广州超云科技有限公司 | Server with high-density GPU expansion capability |
| CN110825193A (en) * | 2019-12-24 | 2020-02-21 | 加弘科技咨询(上海)有限公司 | Method for connecting expansion card, adapter card module and server applied by adapter card module |
Non-Patent Citations (1)
| Title |
|---|
| "面向新硬件的数据处理软件技术";涂云山 等;《华东师范大学学报(自然科学版)》;20180925(第05期);38-48+86 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN112597094A (en) | 2021-04-02 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN112543925B (en) | Unified address space for multiple hardware accelerators using dedicated low latency links | |
| US10411953B2 (en) | Virtual machine fault tolerance method, apparatus, and system | |
| US8745238B2 (en) | Virtual hot inserting functions in a shared I/O environment | |
| US7424564B2 (en) | PCI—express slot for coupling plural devices to a host system | |
| CN108647104B (en) | Request processing method, server and computer readable storage medium | |
| CN114546913B (en) | Method and device for high-speed data interaction between multiple hosts based on PCIE interface | |
| US9021125B2 (en) | Control path I/O virtualisation | |
| US10735294B2 (en) | Integrating a communication bridge into a data processing system | |
| CN112698909A (en) | System, apparatus and method for communicating telemetry information via virtual bus encoding | |
| CN112597094B (en) | Device and method for improving RDMA transmission efficiency | |
| EP2620876B1 (en) | Method and apparatus for data processing, pci-e bus system and server | |
| US11604753B2 (en) | Inter device data exchange via external bus by utilizing communication port | |
| CN110770712B (en) | Operation method, chip, system, readable storage medium and computer program product | |
| CN111427806A (en) | Method for sharing serial port by dual-core AMP system, storage medium and intelligent terminal | |
| CN112463670A (en) | Storage controller access method and related device | |
| CN113572695A (en) | Link aggregation method and device, computing equipment and computer storage medium | |
| CN117749718B (en) | DMA transmission order-preserving processing method and device based on ACK and NOP mechanisms | |
| CN115297198B (en) | Data processing method, circuit, medium and computing device | |
| CN112612733A (en) | Device and method for sharing RAID (redundant array of independent disks) function by multiple machines | |
| CN118740743A (en) | Data transmission method and system | |
| CN114676085A (en) | CCIX (computer communications interface) bus control method, device and medium | |
| CN116055422A (en) | Device and method for controlling data packet sending sequence | |
| CN116436722A (en) | USB virtual network card and server based on PCIE bus | |
| CN118779066A (en) | Virtualization load balancing method and device for Proxmox VE and terminal equipment | |
| CN114490475A (en) | PCI-E adapter card, network card access method, device, equipment and medium |
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 | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |