WO2025066122A1 - 一种多节点服务器架构 - Google Patents

一种多节点服务器架构 Download PDF

Info

Publication number
WO2025066122A1
WO2025066122A1 PCT/CN2024/089401 CN2024089401W WO2025066122A1 WO 2025066122 A1 WO2025066122 A1 WO 2025066122A1 CN 2024089401 W CN2024089401 W CN 2024089401W WO 2025066122 A1 WO2025066122 A1 WO 2025066122A1
Authority
WO
WIPO (PCT)
Prior art keywords
node
connector
heat dissipation
processing unit
module
Prior art date
Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
Pending
Application number
PCT/CN2024/089401
Other languages
English (en)
French (fr)
Inventor
李逸群
余世茂
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Suzhou Metabrain Intelligent Technology Co Ltd
Original Assignee
Suzhou Metabrain Intelligent Technology Co Ltd
Priority date (The priority date 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 date listed.)
Filing date
Publication date
Application filed by Suzhou Metabrain Intelligent Technology Co Ltd filed Critical Suzhou Metabrain Intelligent Technology Co Ltd
Priority to EP24869691.6A priority Critical patent/EP4600837A4/en
Publication of WO2025066122A1 publication Critical patent/WO2025066122A1/zh
Anticipated expiration legal-status Critical
Pending legal-status Critical Current

Links

Classifications

    • G—PHYSICS
    • G06—COMPUTING OR CALCULATING; 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
    • G06F15/161—Computing infrastructure, e.g. computer clusters, blade chassis or hardware partitioning
    • G—PHYSICS
    • G06—COMPUTING OR CALCULATING; COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F1/00—Details not covered by groups G06F3/00 - G06F13/00 and G06F21/00
    • G06F1/16—Constructional details or arrangements
    • G06F1/18—Packaging or power distribution
    • G06F1/181—Enclosures
    • G—PHYSICS
    • G06—COMPUTING OR CALCULATING; COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F1/00—Details not covered by groups G06F3/00 - G06F13/00 and G06F21/00
    • G06F1/16—Constructional details or arrangements
    • G06F1/18—Packaging or power distribution
    • G06F1/183—Internal mounting support structures, e.g. for supporting printed circuit boards
    • G—PHYSICS
    • G06—COMPUTING OR CALCULATING; COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F1/00—Details not covered by groups G06F3/00 - G06F13/00 and G06F21/00
    • G06F1/16—Constructional details or arrangements
    • G06F1/18—Packaging or power distribution
    • G06F1/183—Internal mounting support structures, e.g. for supporting printed circuit boards
    • G06F1/184—Mounting of motherboards
    • G—PHYSICS
    • G06—COMPUTING OR CALCULATING; COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F1/00—Details not covered by groups G06F3/00 - G06F13/00 and G06F21/00
    • G06F1/16—Constructional details or arrangements
    • G06F1/20—Cooling means
    • G—PHYSICS
    • G06—COMPUTING OR CALCULATING; COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F1/00—Details not covered by groups G06F3/00 - G06F13/00 and G06F21/00
    • G06F1/16—Constructional details or arrangements
    • G06F1/20—Cooling means
    • G06F1/206—Cooling means comprising thermal management
    • Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
    • Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
    • Y02D—CLIMATE CHANGE MITIGATION TECHNOLOGIES IN INFORMATION AND COMMUNICATION TECHNOLOGIES [ICT], I.E. INFORMATION AND COMMUNICATION TECHNOLOGIES AIMING AT THE REDUCTION OF THEIR OWN ENERGY USE
    • Y02D10/00—Energy efficient computing, e.g. low power processors, power management or thermal management

Definitions

  • the present application relates to the field of server technology, and in particular to a multi-node server architecture.
  • Servers are an important part of electronic devices and are mainly used to provide computing services. Depending on the type of services provided by the server, servers are mainly divided into file servers, storage servers, database servers, application servers, web servers, etc.
  • Data center equipment mainly includes various types of servers, storage, switches, cabinets and other infrastructure.
  • Each IT equipment is composed of various hardware boards, such as computing modules, storage modules, chassis, cooling modules, etc.
  • PCIE Peripheral Component Interconnect Express, a high-speed serial computer expansion bus standard
  • onboard graphics processors When the internal space of the chassis is the same, the onboard graphics processor solution has a higher degree of integration and occupies relatively less space than the PCIE card solution. It can carry more graphics processor chips and has a higher computing power density. Since the overall size of the onboard graphics processor is larger, when the onboard graphics processor solution is selected, the artificial intelligence server is a multi-node architecture, which puts higher requirements on the maintainability of the server.
  • the purpose of this application is to provide a multi-node server architecture that can minimize the use of data cables, facilitate and quickly perform separate disassembly and maintenance of each node, achieve flexible configuration of each node, and ensure heat dissipation performance.
  • the present application provides a multi-node server architecture, including a server chassis, a pluggable A central processing unit node installed in a server chassis, a data exchange node pluggably installed in the server chassis, a graphics processing unit node pluggably installed in the server chassis, and a mid-backplane module installed in the server chassis.
  • the mid-backplane module is provided with a first connector, a second connector and a third connector for signal interconnection.
  • the central processing unit node is plugged in with the first connector
  • the data exchange node is plugged in with the second connector
  • the graphics processing unit node is plugged in with the third connector.
  • the central processing unit node, the data exchange node and the graphics processing unit node are vertically layered in the server chassis; the first connector, the second connector and the third connector are vertically layered on the mid-backplane module.
  • it also includes a power supply module and a heat dissipation module that are pluggably installed in the server chassis.
  • the mid-backplane module is also provided with a power connector and a heat dissipation control connector.
  • the power supply module is plugged in with the power connector, and the heat dissipation module is plugged in with the heat dissipation control connector.
  • the heat dissipation module includes a heat dissipation fan and a fan backplane, the heat dissipation fan is signal-connected to the fan backplane, and the fan backplane is plug-matched with a heat dissipation control connector.
  • the server chassis includes a first installation cavity located on the front side of the mid-backplane module and a second installation cavity located on the rear side of the mid-backplane module.
  • the central processing unit node, data exchange node and graphics processing unit node are all installed in the first installation cavity, and the power supply module and the heat dissipation module are both installed in the second installation cavity.
  • a first mounting rail assembly, a second mounting rail assembly and a third mounting rail assembly are arranged on the side wall of the server chassis in the first mounting cavity, the central processing unit node can be slidably arranged on the first mounting rail assembly, the data exchange node can be slidably arranged on the second mounting rail assembly, and the graphics processing unit node can be slidably arranged on the third mounting rail assembly.
  • part or all of the first mounting rail assembly, the second mounting rail assembly, and the third mounting rail assembly are guide rails extending along the depth dimension of the server chassis or a plurality of rollers distributed along the depth dimension of the server chassis.
  • a mounting tray connected to the side walls of the server chassis is further disposed in the first mounting cavity for supporting the data exchange node.
  • a plurality of power supply compartments are arranged on the side wall of the server chassis in the second installation cavity, and a plurality of heat dissipation compartments are arranged between the side walls of the server chassis in the second installation cavity.
  • the power supply module can be slidably inserted into the power supply compartment in a vertical posture, and the heat dissipation module can be slidably inserted into the heat dissipation compartment.
  • an elastic baffle is connected to the inner wall of each heat dissipation bin, which is used to elastically reset and close the corresponding heat dissipation bin when the heat dissipation module is pulled out.
  • the CPU node includes a first base and a first mainboard disposed in the first base, a first node connector is disposed at the rear end of the first mainboard, and the first node connector is used to dock with the first connector.
  • the CPU node further includes a first front window disposed at the front end of the first base, and a first rotatable operating handle is disposed on a side of the first front window.
  • the data exchange node includes a second base and a second mainboard disposed in the second base, a second node connector is disposed at the rear end of the second mainboard, and the second node connector is used to dock with the second connector.
  • the data exchange node further includes a function expansion module disposed in the second base, an expansion connector is disposed at the front end of the second mainboard, and the function expansion module is plugged into and matched with the expansion connector.
  • the outer side wall of the second base is provided with a second slide rail extending along the depth dimension direction thereof.
  • the second slide rail is used to cooperate with a second mounting rail assembly arranged on the side wall of the server chassis.
  • a second transition connecting plate is provided at the front end of the side wall of the second base, and a second operating handle that can be flipped is provided on the second transition connecting plate, as well as a second limiting column for abutting against the second operating handle at a preset flipping position.
  • the graphics processor node includes a third base, a third mainboard disposed in the third base, a third node connector is disposed at the rear end of the third mainboard, and the third node connector is used to dock with the third connector.
  • the graphics processor node further includes a third top cover inverted on the third base, short folded edges are erected on both sides of the third base, and side panels on both sides of the third top cover are detachably connected to corresponding short folded edges.
  • a third slide rail extending along the depth dimension direction is disposed on the outer side wall of the third base, and the third slide rail is used to cooperate with a third mounting rail assembly disposed on the side wall of the server chassis.
  • a third transition connecting plate is provided at the front end of the side wall of the third base, and a third flippable operating handle and a third limiting column for abutting the third operating handle at a preset flipping position are provided on the third transition connecting plate.
  • a third front window is provided at the front end of the third base, and a locking piece detachably connected to the third front window is provided on the third operating handle for locking the third operating handle on the third front window when the third operating handle is not flipped over.
  • an elastic member connected to the rotating shaft of the third operating handle is further provided on the third transition connecting plate, and is used to pre-flip the third operating handle to a preset angle by elastic force when the locking member is unlocked.
  • a pressable locking pin is protruding from the outer wall of the side plate of the third top cover, and a limiting block is protruding from the inner wall of the server chassis, and the limiting block is used to abut against the locking pin.
  • the inner end of the locking pin is connected to an elastic strip
  • one end of the elastic strip is connected to the inner wall of the side plate of the third top cover
  • a limiting plate is provided on the inner wall of the side plate of the third top cover at the other end of the elastic strip, and the limiting plate is used to form abutment with the other end of the elastic strip.
  • the middle backplane module includes a front backplane and a rear backplane connected as one body, the first connector, the second connector and the third connector are all arranged on the front backplane, and the power connector and the heat dissipation control connector are both arranged on the rear backplane.
  • the multi-node server architecture provided in this application mainly includes a server chassis, a central processing unit node, a data exchange node, a graphics processing unit node and a mid-backplane module.
  • the server chassis is the main component of this server architecture, which is mainly used to install and carry the remaining server components.
  • the central processing unit node is installed in the server chassis and forms a pluggable connection with the server chassis, that is, it can realize the insertion and installation operation and the unplugging and disassembly operation by reciprocating linear movement in the server chassis, and can conveniently perform disassembly and assembly operations on the server chassis.
  • the central processing unit node is mainly used to realize functions such as data interaction and global control.
  • the graphics processing unit node is installed in the server chassis and forms a pluggable connection with the server chassis, that is, it can realize the insertion and installation operation and the unplugging and disassembly operation by reciprocating linear movement in the server chassis, and can conveniently perform disassembly and assembly operations on the server chassis.
  • the graphics processing unit node is mainly used for AI graphic data calculation.
  • the data exchange node is installed in the server chassis and forms a pluggable connection with the server chassis, that is, it can realize the insertion and installation operation and the removal and removal operation by reciprocating linear movement in the server chassis, and can be conveniently performed on the server chassis.
  • the data exchange node is mainly used to realize data interaction and communication between the central processing unit node and the graphics processing unit node, that is, the central processing unit node and the graphics processing unit node do not directly communicate data, but indirectly communicate data through the data exchange node.
  • the midplane module is also installed in the server chassis, mainly used to realize the unified transfer of data between the central processing unit node and the data exchange node and between the graphics processing unit node and the data exchange node.
  • a first connector, a second connector and a third connector are provided on the midplane module.
  • the first connector, the second connector and the third connector maintain signal interconnection, and the first connector is mainly used to form a plug-in fit with the central processing unit node, thereby realizing the signal connection between the central processing unit node and the mid-backplane module; the second connector is mainly used to form a plug-in fit with the data exchange node, thereby realizing the signal connection between the data exchange node and the mid-backplane module; the third connector is mainly used to form a plug-in fit with the graphics processor node, thereby realizing the signal connection between the graphics processor node and the mid-backplane module.
  • the beneficial effect of the present application is that: since the central processing unit node, the data exchange node and the graphics processing unit node are all connected to the server chassis through plug-in, and the central processing unit node, the data exchange node and the graphics processing unit node are respectively connected to the mid-backplane module through plug-in cooperation with the first connector, the second connector and the third connector, the indirect data communication between the central processing unit node and the graphics processing unit node is realized by using the mid-backplane module and the data exchange node, so that there is basically no need to use any data cables for interconnection between the nodes.
  • the use of data cables can be minimized, thereby overcoming the problem of data cables occupying ventilation area and ensuring heat dissipation performance;
  • the central processing unit node, the data exchange node and the graphics processing unit node can be conveniently disconnected from the first connector, the second connector and the third connector respectively, so that the central processing unit node, the data exchange node and the graphics processing unit node can be separately unplugged from the server chassis, so that each node can be conveniently and quickly disassembled and maintained separately, thereby realizing flexible configuration of each node.
  • the entire graphics processor node forms an inverted structure
  • the third mainboard equipped with the GPU chip can be directly installed into the third base from top to bottom along the vertical direction during the assembly process, and fixed by fasteners such as screws, without the need for other horizontal sliding movements or other installation operations, and finally the third top cover is inverted on the short folded edge to complete the assembly; the side wall height of the third base is relatively low, which can shorten the installation stroke and simplify the installation steps of the third mainboard, thereby improving the assembly efficiency of the production line.
  • the third mainboard is easy to disassemble and has better maintainability, and also reduces the probability of the risk of bumping the third mainboard during the assembly process.
  • the multi-node server architecture provided by the present application can minimize the use of data cables, conveniently and quickly perform separate disassembly and maintenance operations on each node, achieve flexible configuration of each node, and ensure heat dissipation performance.
  • FIG1 is an exploded view of the overall structure of some specific implementation methods provided in this application.
  • FIG. 2 is a schematic diagram of the overall structure of some specific implementation methods provided in this application.
  • FIG. 3 is a schematic diagram of FIG. 2 from another viewing angle.
  • FIG. 4 is a schematic diagram of the front structure of a server chassis.
  • FIG. 5 is a schematic diagram of the structure after the installation tray is removed from FIG. 4 .
  • FIG. 6 is a schematic diagram of the rear end structure of the server chassis.
  • FIG. 7 is a schematic diagram of the specific structure of a central processing unit node.
  • FIG. 8 is an exploded view of the structure of FIG. 7 .
  • FIG. 9 is an enlarged view of the local structure of FIG. 7 .
  • FIG. 10 is a schematic diagram of a specific structure of a data exchange node.
  • FIG. 11 is an exploded view of the structure of FIG. 10 .
  • FIG. 12 is an enlarged view of the local structure of FIG. 10 .
  • FIG. 13 is an exploded diagram of the specific structure of a graphics processor node.
  • FIG. 14 is a schematic diagram of a specific structure of a graphics processor node.
  • FIG. 15 is a schematic diagram of a partial structure of FIG. 14 .
  • FIG. 16 is a schematic diagram of the specific structure of the third base.
  • FIG. 17 is a schematic diagram of the flipping state of the third operating handle.
  • FIG. 18 is a schematic diagram showing a comparison of front and rear viewing angles of the third front window.
  • FIG. 19 is a schematic diagram of the specific structure of the third top cover.
  • FIG. 20 is a structural diagram of FIG. 19 from another perspective.
  • FIG. 21 is a schematic diagram of the installation process of a graphics processor node.
  • FIG. 22 is a schematic diagram showing the front and rear viewing angle comparison of the mid-back panel module.
  • FIG. 1 to 22 The first installation cavity—a, the second installation cavity—b; Server chassis—1, central processing unit node—2, data exchange node—3, graphics processing unit node—4, mid-backplane module—5, power module—6, heat dissipation module—7;
  • Figure 1 is a schematic diagram of the overall structure of some specific implementation methods provided in this application
  • Figure 2 is a schematic diagram of the overall structure of some specific implementation methods provided in this application.
  • the multi-node server architecture mainly includes a server chassis 1, a central processing unit node 2, a data exchange node 3, a graphics processing unit node 4 and a mid-backplane module 5.
  • the server chassis 1 is the main component of the server architecture, and is mainly used to install and carry other server components.
  • the CPU node 2 is installed in the server chassis 1 and forms a pluggable connection with the server chassis 1, that is, it can be inserted and installed and pulled out and removed by reciprocating linear movement in the server chassis 1, and can be easily installed and removed from the server chassis 1.
  • the CPU node 2 is mainly used to realize functions such as data interaction and global control.
  • the graphics processor node 4 is installed in the server chassis 1 and forms a pluggable connection with the server chassis 1, that is, it can be inserted and installed and pulled out and removed by reciprocating linear movement in the server chassis 1, and can be easily disassembled and assembled on the server chassis 1.
  • the graphics processor node 4 is mainly used for AI graphics data calculation.
  • the data exchange node 3 is installed in the server chassis 1 and forms a pluggable connection with the server chassis 1, that is, it can realize the insertion and installation operation and the removal and removal operation by reciprocating linear movement in the server chassis 1, and can conveniently perform the disassembly and assembly operation on the server chassis 1.
  • the data exchange node 3 is mainly used to realize the data interaction and communication between the central processing unit node 2 and the graphics processing unit node 4, that is, the central processing unit node 2 and the graphics processing unit node 4 do not directly communicate data, but indirectly communicate data through the data exchange node 3.
  • the middle backplane module 5 is also installed in the server chassis 1, and is mainly used to realize the unified data transfer between the central processing unit node 2 and the data exchange node 3, and between the graphics processing unit node 4 and the data exchange node 3.
  • the middle backplane module 5 is provided with a first connector 51, a second connector 52 and a third connector 53, and the first connector 51, the second connector 52 and the third connector 53 are interconnected by signals, and the first connector 51 is mainly used to form a plug-in fit with the central processing unit node 2, thereby realizing the signal connection between the central processing unit node 2 and the middle backplane module 5; the second connector 52 is mainly used to form a plug-in fit with the data exchange node 3, thereby realizing the signal connection between the data exchange node 3 and the middle backplane module 5; the third connector 53 is mainly used to form a plug-in fit with the graphics processing unit node 4, thereby realizing the signal connection between the graphics processing unit node 4 and the middle backplane module 5.
  • the multi-node server architecture provided by this embodiment, since the central processing unit node 2, the data exchange node 3 and the graphics processing unit node 4 are all connected to the server chassis 1 by plugging, and the central processing unit node 2, the data exchange node 3 and the graphics processing unit node 4 are connected to the mid-backplane module 5 by plugging and matching with the first connector 51, the second connector 52 and the third connector 53, respectively, the indirect data communication between the central processing unit node 2 and the graphics processing unit node 4 is realized by using the mid-backplane module 5 and the data exchange node 3, so that there is basically no need to use any data cables for interconnection between the nodes.
  • the use of data cables can be minimized, thereby overcoming the problem of data cables occupying ventilation area and ensuring heat dissipation performance;
  • the central processing unit node 2, the data exchange node 3 and the graphics processing unit node 4 can be conveniently disconnected from the first connector 51, the second connector 52 and the third connector 53, respectively, so that the central processing unit node 2, the data exchange node 3 and the graphics processing unit node 4 can be separately unplugged from the server chassis 1, and then the separate disassembly and maintenance operations of each node can be conveniently and quickly performed, and flexible configuration of each node can be achieved.
  • the multi-node server architecture provided in this embodiment can minimize the use of data cables, conveniently and quickly perform separate disassembly and maintenance operations on each node, achieve flexible configuration of each node, and ensure heat dissipation performance.
  • the central processing unit node 2 In order to facilitate the plug-in and unplug operations of the central processing unit node 2, the data exchange node 3 and the graphics processing unit node 4, in this embodiment, the central processing unit node 2, the data exchange node 3 and the graphics processing unit node 4 are specifically distributed in a vertical layer in the server chassis 1, that is, they are horizontally arranged and distributed along the height direction.
  • the central processing unit node 2 is located in the upper layer
  • the data exchange node 3 is located in the middle layer
  • the graphics processing unit node 4 is located in the bottom layer, etc.
  • the first connector 51, the second connector 52 and the third connector 53 are also distributed in a vertical layer on the middle backplane module 5, that is, they are distributed along the height direction of the middle backplane module 5, and the distribution form of the first connector 51, the second connector 52 and the third connector 53 on the middle backplane module 5 corresponds to the distribution form of the central processing unit node 2, the data exchange node 3 and the graphics processing unit node 4 in the server chassis 1, so as to ensure that they can correspond correctly one by one.
  • the CPU nodes 2 , the data exchange nodes 3 and the GPU nodes 4 are not limited to being distributed in a vertical layer in the server chassis 1 .
  • they may be distributed vertically along the depth direction of the server chassis 1 .
  • FIG. 3 is a schematic diagram of FIG. 2 from another viewing angle.
  • a power module 6 and a heat dissipation module 7 are added in this embodiment.
  • the power module 6 is installed in the server chassis 1 and forms a pluggable connection with the server chassis 1, that is, it can realize the insertion and installation operation and the pull-out and disassembly operation by reciprocating linear movement in the server chassis 1, and can be conveniently performed on the server chassis 1.
  • the power module 6 is mainly used to realize the power supply to the remaining server components.
  • the heat dissipation module 7 is installed in the server chassis 1 and forms a pluggable connection with the server chassis 1, that is, it can realize the insertion and installation operation and the pull-out and disassembly operation by reciprocating linear movement in the server chassis 1, and can be conveniently performed on the server chassis 1.
  • the heat dissipation module 7 is mainly used to realize air cooling and heat dissipation of the remaining server components.
  • the heat dissipation module 7 can also dissipate the heat of the remaining server components by liquid cooling.
  • a power connector 54 and a heat dissipation control connector 55 are added to the middle backplane module 5.
  • the power connector 54 is mainly used to form a plug-in match with the power module 6, thereby realizing the electrical connection between the power module 6 and the middle backplane module 5.
  • the heat dissipation control connector 55 is mainly used to form a plug-in match with the heat dissipation module 7, thereby realizing the signal connection between the heat dissipation module 7 and the middle backplane module 5.
  • the heat dissipation module 7 mainly includes a heat dissipation fan 71 and a fan backplane 72.
  • the heat dissipation fan 71 forms a signal connection with the fan backplane 72
  • the fan backplane 72 forms a plug-in match with the heat dissipation control connector 55 on the middle backplane module 5 through a connector.
  • the central processing unit node 2 can form a signal connection with the heat dissipation fan 71 through the heat dissipation control connector 55 on the middle backplane module 5, so as to conveniently control the heat dissipation state of the heat dissipation fan 71.
  • FIG. 4 is a schematic diagram of the front structure of the server chassis 1
  • FIG. 5 is a schematic diagram of the structure after the installation tray 14 is removed from FIG. 4 .
  • the internal space of the server chassis 1 mainly includes a first installation cavity a and a second installation cavity b.
  • the first installation cavity a and the second installation cavity b are separated by the middle backplane module 5.
  • the first installation cavity a is located in front of the middle backplane module 5, and is also the front space of the server chassis 1, which is mainly used to install core components such as the central processing unit node 2, the data exchange node 3 and the graphics processing unit node 4;
  • the second installation cavity b is located behind the middle backplane module 5, and is also the rear space of the server chassis 1, which is mainly used to install other auxiliary server components such as the power module 6 and the heat dissipation module 7.
  • the middle backplane module 5 is used to divide the internal space of the server chassis 1 into two parts, thereby separating each core component from the other auxiliary server components to avoid installation interference and heat dissipation effects.
  • the server chassis 1 is 6U in height, while the CPU node 2 usually occupies 1U in height.
  • Point 3 usually occupies a 2U height, and GPU node 4 usually occupies a 3U height.
  • the first installation cavity a of the server chassis 1 specifically includes a first node installation cavity, a second node installation cavity and a third node installation cavity.
  • the first node installation cavity is mainly used to install the central processing unit node 2
  • the second node installation cavity is mainly used to install the data exchange node 3
  • the third node installation cavity is mainly used to install the graphics processing unit node 4.
  • the first node installation cavity is located in the upper area of the first installation cavity a
  • the second node installation cavity is located in the middle area of the first installation cavity a
  • the third node installation cavity is located in the lower area of the first installation cavity a.
  • the first node installation cavity, the second node installation cavity and the third node installation cavity form a hierarchical distribution in the vertical direction in the first installation cavity a, and do not affect each other.
  • the vertical distribution form of the first node installation cavity, the second node installation cavity and the third node installation cavity can also be flexibly adjusted, and the relative relationship between the upper and lower positions is not fixed.
  • the first node installation cavity is located in the middle area of the first installation cavity a
  • the second node installation cavity is located in the upper area of the first installation cavity a
  • the third node installation cavity is located in the lower area of the first installation cavity a, etc.
  • first node installation cavity, the second node installation cavity and the third node installation cavity are not limited to forming a vertical hierarchical distribution in the first installation cavity a.
  • they can also be distributed in parallel along the depth direction of the server chassis 1.
  • the central processing unit node 2, the data exchange node 3 and the graphics processing unit node 4 are respectively installed in the first installation cavity a in a vertical posture along the vertical direction.
  • first installation cavity a of the server chassis 1 is not limited to including the first node installation cavity, the second node installation cavity and the third node installation cavity.
  • first installation cavity a may also include more node installation cavities.
  • the internal space of the server chassis 1 includes an intermediate installation cavity (not shown in the figure) in addition to the first installation cavity a and the second installation cavity b.
  • the intermediate installation cavity is located between the first installation cavity a and the second installation cavity b, separating the two from each other, and is mainly used to install the middle backplane module 5.
  • the depth dimension (or width) of the middle installation cavity is narrow so as to match the size of the middle backplane module 5, and vertically extending sliding grooves are provided on the side walls on both sides of the middle installation cavity, so that the middle backplane module 5 can slide vertically into the middle installation cavity, thereby realizing the sliding plug-in installation of the middle backplane module 5 in the server chassis 1.
  • the middle backplane module 5 can also be reinforced with fasteners such as screws in the installation cavity, or positioning can be achieved in the installation cavity by cooperating with positioning holes on the middle backplane module 5 through positioning pins and other components.
  • a first mounting track assembly 11, a second mounting track assembly 12, and a third mounting track assembly 13 are added in this embodiment.
  • the central processing unit node 2 is specifically arranged on the first mounting track assembly 11, and forms a sliding connection with the first mounting track assembly 11, and can slide along the first mounting track assembly 11, and then the installation and removal operations of the central processing unit node 2 in the server chassis 1 are realized along the first mounting track assembly 11.
  • the data exchange node 3 is specifically arranged on the second mounting track assembly 12, and forms a sliding connection with the second mounting track assembly 12, and can slide along the second mounting track assembly 12, and then the installation and removal operations of the data exchange node 3 in the server chassis 1 are realized along the second mounting track assembly 12.
  • the graphics processing unit node 4 is specifically arranged on the third mounting track assembly 13, and forms a sliding connection with the third mounting track assembly 13, and can slide along the third mounting track assembly 13, and then the installation and removal operations of the graphics processing unit node 4 in the server chassis 1 are realized along the third mounting track assembly 13.
  • the central processing unit node 2, the data exchange node 3 and the graphics processing unit node 4 each correspond to an installation track, and can slide on their respective installation tracks, ensuring that the plugging, unplugging, and disassembling operations of the central processing unit node 2, the data exchange node 3 and the graphics processing unit node 4 are independent of each other and do not affect each other, thereby realizing the separate disassembly, assembly, maintenance, and personalized configuration adjustment of the three.
  • the first mounting rail assembly 11, the second mounting rail assembly 12 and the third mounting rail assembly 13 are specifically guide rails extending along the depth dimension direction of the server chassis 1, or are multiple rollers distributed along the depth dimension direction of the server chassis 1.
  • the first mounting track component 11 is specifically the above-mentioned guide rail
  • the second mounting track component 12 and the third mounting track component 13 are specifically multiple rollers, etc.
  • the CPU node 2 when the CPU node 2, the data exchange node 3 and the graphics processor node 4 are respectively mounted on the first mounting track component 11, the second mounting track component 12 and the third mounting track component 13, it can ensure that the three maintain a horizontal posture during the plugging and unplugging movement, and achieve stable plugging and unplugging operations; at the same time, when multiple roller structures are used, the friction and wear of the CPU node 2, the data exchange node 3 and the graphics processor node 4 can also be reduced by rolling friction, thereby improving the smoothness of movement.
  • an installation tray 14 is added in this embodiment.
  • the installation tray 14 is arranged in the first safety cavity of the server chassis 1, and is specifically connected to the side walls of the server chassis 1. It is mainly used to support the installation of the data exchange node 3, and assist the second installation track assembly 12 to improve the installation stability of the data exchange node 3. Of course, the installation tray 14 does not interfere with the movement of the data exchange node 3 on the second installation track assembly 12.
  • FIG. 6 is a schematic diagram of the rear end structure of the server chassis 1 .
  • a power supply compartment 15 and a heat dissipation compartment 16 are additionally provided in the server chassis 1 in this embodiment.
  • the power supply compartment 15 is arranged in the second installation cavity b of the server chassis 1, specifically on the side wall of the server chassis 1, and is vertically distributed close to the side wall of the server chassis 1.
  • multiple power supply compartments 15 are arranged at the same time, such as 3 to 6. Accordingly, the power supply module 6 needs to be installed in the power supply compartment 15 in a vertical posture, and form a sliding connection with the bottom plate of the power supply compartment 15, and can slide into the power supply compartment 15 or slide out of the power supply compartment 15 along the bottom plate of the power supply compartment 15.
  • each power supply module 6 reasonably utilizes the side space of the server chassis 1, reduces the occupation of the middle installation space of the server chassis 1, and improves the space utilization rate.
  • the heat dissipation chamber 16 is also arranged in the second installation cavity b of the server chassis 1, specifically located in the middle area of the server chassis 1. Generally, multiple heat dissipation chambers 16 are arranged at the same time, and form a matrix distribution in the vertical and width directions according to certain specifications, such as a 3 ⁇ 4 distribution. Accordingly, the heat dissipation module 7 can be installed in the heat dissipation chamber 16, and form a sliding connection with the bottom plate of the heat dissipation chamber 16, and can slide into the heat dissipation chamber 16 or slide out of the heat dissipation chamber 16 along the bottom plate of the heat dissipation chamber 16.
  • the fan back plate 72 is also installed in the second installation cavity b of the server chassis 1, specifically located at the rear of the heat dissipation chamber 16, so that the fan back plate 72 can be conveniently connected to the heat dissipation fan 71 installed in the heat dissipation chamber 16.
  • a fan back plate 72 is simultaneously connected to each heat dissipation fan 71 in the same layer of the heat dissipation chamber 16, for example, a fan back plate 72 is connected to three heat dissipation fans 71, etc.
  • the number of heat dissipation modules 7 can be controlled by plugging and unplugging the heat dissipation modules 7 in the heat dissipation chamber 16, so that the upper limit of the heat dissipation performance of the server can be conveniently adjusted.
  • the present embodiment also adds an elastic baffle 17 in each heat dissipation bin 16. Specifically, one end of the elastic baffle 17 is connected to the inner wall of the heat dissipation bin 16, such as the top wall of the heat dissipation bin 16, and the other end extends toward the relative inner wall, such as to the bottom wall of the heat dissipation bin 16, and is elastic.
  • the heat dissipation module 7 When the heat dissipation module 7 is inserted into the heat dissipation bin 16, it will abut against the elastic baffle 17 and elastically deform it to be tightly attached to the inner wall of the heat dissipation bin 16, so that the elastic baffle 17 cannot block the ventilation area of the heat dissipation bin 16; and when the heat dissipation module 7 is pulled out of the heat dissipation bin 16, the elastic baffle 17 rebounds under the action of the elastic force and closes the heat dissipation bin 16, which is equivalent to closing the corresponding heat dissipation bin 16 and reducing the ventilation area to zero.
  • a top cover plate 19 is provided on the top of the server chassis 1.
  • the top cover plate 19 mainly includes a front upper cover, a middle upper cover and a thick upper cover.
  • the front upper cover is located in each node area
  • the middle upper cover is located in the middle backplane module 5 area
  • the rear upper cover is located in the power module 6 area.
  • the front upper cover and the rear upper cover are fixed to the side wall of the server chassis 1 by fasteners such as rivets
  • the middle upper cover is positioned on the side wall of the server chassis 1 by I-shaped nails, and then fixed to the side wall of the server chassis 1 by the upper cover lock.
  • the present embodiment also provides a carrying handle 110 on the side wall of the server chassis 1.
  • the carrying handle 110 can be flipped and stored on the side wall of the server chassis 1. When it is needed, it can be grasped and used by simply flipping it outward.
  • FIG. 7 is a schematic diagram of a specific structure of the central processing unit node 2
  • FIG. 8 is an exploded diagram of the structure of FIG. 7 .
  • the central processing unit node 2 mainly includes a first base 21 and a first mainboard 22.
  • the first base 21 is the bottom component of the central processing unit node 2, which is mainly used to carry other components.
  • the first mainboard 22 is installed with server components such as a central processing unit, a memory stick, and a network card, and in order to facilitate the signal connection between the first mainboard 22 and the mid-backplane module 5, a first node connector 23 is provided at the rear end of the first mainboard 22.
  • the first node connector 23 is mainly used to dock with the first connector 51 on the mid-backplane module 5, so as to realize the signal connection between the first mainboard 22 and the mid-backplane module 5.
  • FIG. 9 is an enlarged view of the local structure of FIG. 7 .
  • the CPU node 2 also includes a first front window 24 and a first operating handle 25.
  • the first front window 24 is set at the front end position of the first base 21, and the first operating handle 25 is set at the side position of the first front window 24, such as being set on both sides of the first front window 24 at the same time, or only being set on one side of the first front window 24.
  • the first operating handle 25 forms a rotation connection with the side of the first front window 24, so that the first operating handle 25 can perform horizontal rotation relative to the first front window 24.
  • the first operating handle 25 rotates to be close to the outer side surface of the first front window 24 to achieve storage, and is fixed by fasteners such as hand-tightened bolts; in the plug-in and unplug operation state, the first operating handle 25 rotates to the outer side surface away from the first front window 24 and toward the front end of the first base 21, so that the staff can grasp and apply force with their hands, and then insert the entire CPU node 2 into the server chassis 1, or pull the entire CPU node 2 out of the server chassis 1.
  • a first bottom tray 26 is additionally provided in the first base 21 for supporting and installing the first mainboard 22.
  • a plurality of heat dissipation holes can also be provided on the first front window 24 to enhance ventilation and heat dissipation.
  • a first top cover 27 is also provided on the top of the first base 21. The first top cover 27 is inserted into the top slot of the side wall of the first base 21 by means of I-shaped nails and other components for positioning and then fixed to the first base 21 by means of a push-type top cover lock.
  • a connector positioning hole is also provided at the rear end of the first mainboard 22 for positioning with the positioning column 418 provided on the mid-backplane module 5.
  • a positioning notch is also provided at the rear end of the first base 21 for positioning with I-shaped nails and other components provided inside the server chassis 1, thereby realizing the installation and positioning of the entire central processing unit node 2 in the server chassis 1.
  • FIG. 10 is a schematic diagram of a specific structure of the data exchange node 3
  • FIG. 11 is an exploded diagram of the structure of FIG. 10 .
  • the data exchange node 3 mainly includes a second base 31 and a second mainboard 32.
  • the second base 31 is the bottom component of the data exchange node 3, and is mainly used to carry other components.
  • the second mainboard 32 is installed with server components such as a data processing module, and in order to facilitate the signal connection between the second mainboard 32 and the mid-backplane module 5, a second node connector 33 is provided at the rear end of the second mainboard 32.
  • the second node connector 33 is mainly used to dock with the second connector 52 on the mid-backplane module 5, so as to realize the signal connection between the second main board 32 and the mid-backplane module 5.
  • the present embodiment adds a function expansion module 34 in the data exchange node 3.
  • the function expansion module 34 is arranged in the second base 31, such as at the front end of the second base 31, and can be a PCIE module or other types of expansion modules, such as a PCIE card equipped with a GPU chip or a PCIE card equipped with a network chip.
  • the function expansion module 34 is specifically arranged at the front end of the second base 31, and the second mainboard 32 is specifically arranged at the rear end of the second base 31.
  • the present embodiment also provides an expansion connector 35 at the front end of the second mainboard 32.
  • the expansion connector 35 is mainly used to form a plug-in match with the connector on the function expansion module 34, so as to realize the signal connection between the function expansion module 34 and the second mainboard 32, and facilitate the disassembly and assembly operation between the function expansion module 34 and the second mainboard 32, thereby realizing flexible configuration.
  • a second slide rail 36 is added in this embodiment.
  • the second slide rail 36 is arranged on the outer wall of the second base 31, and can be arranged on only one side or on both sides at the same time. Specifically, it extends a preset length along the depth dimension direction (usually the length direction) of the second base 31, and is mainly used to cooperate with the second mounting rail assembly 12 set on the side wall of the server chassis 1.
  • the second slide rail 36 can slide along the second mounting rail assembly 12, thereby guiding the plugging and unplugging movement of the data exchange node 3.
  • the second slide rail 36 can form rolling friction with each roller at the same time.
  • FIG. 12 is an enlarged view of the local structure of FIG. 10 .
  • a second transition connecting plate 37 and a second operating handle 38 are added in this embodiment.
  • the second transition connecting plate 37 is arranged at the front end position of the side wall of the second base 31, for example, it is arranged on both sides of the second base 31 at the same time, or it is arranged only on one side of the second base 31.
  • the second operating handle 38 is arranged on the second transition connecting plate 37, and forms a rotation connection with the second transition connecting plate 37, and can be flipped relative to the second transition connecting plate 37.
  • the second operating handle 38 flips to a vertical posture and is stored on the outer side of the second transition connecting plate 37, and can also be fixed by fasteners such as hand-tightened bolts; in the plug-in and unplug operation state, the second operating handle 38 flips outward to be away from the second transition connecting plate 37, and presents a preset inclination posture, and the whole faces the front of the second base 31, so that the staff can grasp and apply force with their hands, and then insert the entire data exchange node 3 into the server chassis 1, or pull the entire data exchange node 3 out of the server chassis 1.
  • a second limiting column 39 is added in this embodiment.
  • the second limiting column 39 is arranged on the second transition connecting plate 37, specifically located in the rear area of the second operating handle 38, and is mainly used to form abutment with the rear end of the second operating handle 38 when the second operating handle 38 is turned outward to a preset angle, so that the second operating handle 38 cannot be turned outward, thereby limiting the maximum outward turning angle of the second operating handle 38.
  • the maximum outward turning angle of the second operating handle 38 can be between 30 and 60 degrees.
  • heat dissipation holes are provided on the side wall of the second base 31, and an air guide cover is provided inside the second base 31 to enhance ventilation and heat dissipation performance.
  • a reinforcing crossbeam is provided at the rear end of the second base 31 to enhance structural strength.
  • a second top cover 310 is provided on the top of the second base 31, and the second top cover 310 is positioned and matched with the corresponding slot on the top of the side wall of the second base 31 by means of I-shaped nails and other components, and then the second top cover 310 is fixed to the second base 31 by means of a top cover lock.
  • a second bottom tray 311 is also provided in the second base 31 to support and install the second mainboard 32.
  • a hard disk module 312 can also be provided at the front end of the second base 31.
  • the hard disk module 312 can generally be used to install 4 to 8 vertically inserted 2.5-inch hard disks.
  • the hard disks are connected to the hard disk backplane and then connected to the second mainboard 32 via data cables.
  • FIG. 13 is an exploded view of the specific structure of the graphics processor node 4
  • FIG. 14 is a schematic diagram of the specific structure of the graphics processor node 4
  • FIG. 15 is a schematic diagram of the partial structure of FIG. 14 .
  • the graphics processor node 4 mainly includes a third base 41 and a third mainboard 42.
  • the third base 41 is the bottom component of the graphics processor node 4, which is mainly used to carry other components.
  • Server components such as GPU chips are installed on the third mainboard 42, and in order to facilitate the signal connection between the third mainboard 42 and the middle backplane module 5, a third node connector 43 is provided at the rear end of the third mainboard 42.
  • the third node connector 43 is mainly used to dock with the third connector 53 on the middle backplane module 5, so as to realize the signal connection between the third mainboard 42 and the middle backplane module 5.
  • FIG. 16 is a schematic diagram of the specific structure of the third base 41
  • FIG. 21 is a schematic diagram of the installation process of the graphics processor node 4 .
  • this embodiment adds a third top cover 44 and a short folding edge 45 to the graphics processor node 4.
  • the third top cover 44 is similar to the aforementioned first top cover 2719 and the second top cover 310, and is a cover structure of the third base 41, but the difference is that the height of the side panels on both sides of the third top cover 44 is relatively large, and is significantly greater than the height of the short folding edge 45, and can be inverted on the third base 41 for installation.
  • the short folding edge 45 is vertically arranged on the side positions of the two sides of the third base 41, and its height is relatively low, which is equivalent to the two side folding edges of the third base 41, so that the third base 41 is closer to a flat plate or disc shape.
  • the side panels of the third top cover 44 are detachably connected to the short folds 45 on both sides.
  • the entire graphics processor node 4 forms an inverted structure, and the third motherboard 42 equipped with the GPU chip can be directly installed vertically from top to bottom into the third base 41 during the assembly process, and fixed by fasteners such as screws, without other horizontal sliding movements or other installation operations.
  • the third top cover 44 is inverted on the short folds 45 to complete the assembly; the side wall height of the third base 41 is relatively low, which can shorten the installation stroke and simplify the installation steps of the third motherboard 42, thereby improving the assembly efficiency of the production line.
  • the third motherboard 42 is easy to disassemble, has better maintainability, and also reduces the probability of the third motherboard being bumped during the assembly process.
  • a positioning groove 419 is provided at the top of the short fold 45, and components such as I-shaped nails are provided at the bottom of the third top cover 44 to cooperate with the positioning groove 419 to achieve installation and positioning.
  • a plurality of threaded holes are also provided on the side wall of the short fold 45 to form a threaded connection with the side panels of the third top cover 44.
  • a third slide rail 46 is added in this embodiment.
  • the third slide rail 46 is set on the outer wall of the third base 41, and can be set on only one side or on both sides at the same time. Specifically, it extends along the depth dimension direction (usually the length direction) of the third base 41 by a preset length, and is mainly used to cooperate with the third mounting rail assembly 13 set on the side wall of the server chassis 1.
  • the third slide rail 46 slides along the third mounting rail assembly 13, thereby guiding the plugging and unplugging movement of the GPU node 4.
  • the third slide rail 46 can form rolling friction with each roller at the same time.
  • FIG. 17 is a schematic diagram of the flipping state of the third operating handle 48 .
  • a third transition connecting plate 47 and a third operating handle 48 are added in this embodiment.
  • the third transition connecting plate 47 is arranged at the front end position of the side wall of the third base 41, for example, it is arranged on both sides of the third base 41 at the same time, or it is arranged only on one side of the third base 41.
  • the third transition connecting plate 47 is also used to realize the installation of the third front window 410 at the front end of the third base 41.
  • the third operating handle 48 is arranged on the third transition connecting plate 47, and forms a rotation connection with the third transition connecting plate 47, and can perform a flipping movement relative to the third transition connecting plate 47.
  • the third operating handle 48 is flipped to a vertical position and is housed on the outer side of the third transition connecting plate 47, and can also be fixed by a locking member 411 such as a hand-tightened bolt; under plugging and unplugging operation conditions, the third operating handle 48 is flipped outward to be away from the third transition connecting plate 47, and is in a preset inclination position, and is facing the front of the third base 41 as a whole, so that the staff can grasp and apply force with their hands, thereby inserting the entire graphics processor node 4 into the server chassis 1, or pulling the entire graphics processor node 4 out of the server chassis 1.
  • a third limiting column 49 is added in this embodiment.
  • the third limiting column 49 is arranged on the third transition connecting plate 47, specifically located in the rear area of the third operating handle 48, and is mainly used to form abutment with the rear end of the third operating handle 48 when the third operating handle 48 is turned outward to a preset angle, so that the third operating handle 48 cannot be turned outward, thereby limiting the maximum outward turning angle of the third operating handle 48.
  • the maximum outward turning angle of the third operating handle 48 can be between 30 and 60 degrees.
  • an elastic member 412 is additionally provided. Specifically, one end of the elastic member 412 is connected to the rotating shaft of the third operating handle 48, and the other end is connected to the outer side wall of the third transition connecting plate 47. When the third operating handle 48 is turned inward to the storage state, the elastic member 412 is compressed and accumulates elastic potential energy.
  • the elastic member 412 can be kept in the compressed state; and when the locking member 411 is unlocked by the staff, the elastic member 412 immediately rebounds, releases the elastic potential energy, and drives the third operating handle 48 to turn outward, that is, the third operating handle 48 is automatically pre-turned to a preset angle by the elastic force, so that it is convenient for the staff to grasp it, and there is no need to turn the third operating handle 48 outward from the storage state, which not only saves effort but also improves the operation efficiency.
  • FIG. 19 is a schematic diagram of the specific structure of the third top cover 44
  • FIG. 20 is a structural diagram of FIG. 19 from another viewing angle.
  • a locking pin 413 and a limiting block 18 are added in this embodiment.
  • the locking pin 413 is set on the outer wall of the side plate of the third top cover 44, and can be set on both side plates of the third top cover 44 at the same time, or can be set only on one side plate of the third top cover 44.
  • the locking pin 413 protrudes from the outer wall of the side plate of the third top cover 44, and can be pressed by the staff.
  • the limiting block 18 is specifically set on the inner wall of the server chassis 1 and protrudes from the inner wall of the server chassis 1, and is mainly used to form abutment with the locking pin 413.
  • an elastic strip 414 and a limit plate 415 are added in this embodiment.
  • the elastic strip 414 is arranged at the inner end of the lock pin 413, and one end of the lock pin 413 is connected to the inner wall of the side plate of the third top cover 44, and the other end of the lock pin 413 extends along the length direction of the side plate of the third top cover 44.
  • the elastic strip 414 is elastically deformed and deflected inward.
  • the limit plate 415 is arranged on the inner wall of the side plate of the third top cover 44, specifically at the other end of the elastic strip 414, and is mainly used to form abutment with the other end of the elastic strip 414, limit the maximum deflection of the elastic strip 414, and thus prevent the lock pin 413 from being pressed too deeply by the staff.
  • a third bottom tray 416 is provided in the third base 41 to support and install the third mainboard 42.
  • a plurality of gourd holes are provided on the third bottom tray 416, and a plurality of positioning posts 418 are provided on the bottom surface of the third base 41.
  • the third bottom tray 416 is positioned and installed on the third base 41 through the cooperation of each gourd hole and each positioning post 418.
  • a positioning groove 419 is provided on the top of the short folding edge 45, and a positioning member 424 such as an I-shaped nail is provided at the bottom of the third top cover 44, so that the third top cover 44 can be positioned and installed on the third base 41 through the cooperation of the positioning groove 419 and the positioning member 424.
  • an air guide 417 is additionally provided in the third base 41.
  • a lap installation slot for installing the air guide 417 and a avoidance hole 420 for the avoidance elastic strip 414 and the limit plate 415 are also provided on the top of the short folding edge 45.
  • an L-shaped reinforcing plate 421 is formed by raising the local area of the short folded edge 45 to improve the connection strength.
  • a positioning notch is provided at the rear end of the third base 41 to achieve positioning installation in the server chassis 1, and a mounting guide plate 425 is also provided at the rear end of the third base 41.
  • the mounting guide plate 425 is inclined and is mainly used for installing the graphics processor node 4.
  • the mounting guide plate 425 is abutted against the server chassis 1 to guide the installation movement of the third base 41, so that it can be installed in the server chassis 1 more smoothly.
  • FIG. 18 is a schematic diagram comparing the front and rear viewing angles of the third front window 410 .
  • the third front window 410 is provided with a plurality of heat dissipation holes to enhance ventilation and heat dissipation performance.
  • a support block 422 is provided on the top of the third front window 410 to support the front end of the third top cover 44 to prevent the front end of the third top cover 44 from sinking.
  • the inner side wall of the third front window 410 is provided with a plurality of reinforcing ribs 423.
  • FIG. 22 is a schematic diagram comparing the front and rear viewing angles of the middle back panel module 5 .
  • the middle backplane module 5 mainly includes a front backplane 56 and a rear backplane 57.
  • the front backplane 56 and the rear backplane 57 are connected as one, and the front backplane 56 faces the front of the server chassis 1, while the rear backplane 57 faces the rear of the server chassis 1.
  • the first connector 51, the second connector 52 and the third connector 53 are all arranged on the front backplane 56, and the power connector 54 and the heat dissipation control connector 55 are all arranged on the rear backplane 57.
  • the first connector 51, the second connector 52 and the third connector 53, as well as the power connector 54 and the heat dissipation control connector 55 are isolated from each other by the front backplane 56 and the rear backplane 57, which can avoid heat concentration and connection confusion.
  • multiple ventilation holes 59 can be provided on the front back plate 56 and the back plate 57 to enhance ventilation and heat dissipation performance.
  • the present embodiment also provides multiple positioning rods 58 on the front back plate 56 and the back plate 57, so as to form a positioning match with the positioning rods 58 and the positioning countersunk holes on the connectors at each node or the power module 6 and the heat dissipation module 7.

Landscapes

  • Engineering & Computer Science (AREA)
  • Theoretical Computer Science (AREA)
  • Physics & Mathematics (AREA)
  • General Engineering & Computer Science (AREA)
  • Computer Hardware Design (AREA)
  • General Physics & Mathematics (AREA)
  • Human Computer Interaction (AREA)
  • Power Engineering (AREA)
  • Mathematical Physics (AREA)
  • Software Systems (AREA)
  • Cooling Or The Like Of Electrical Apparatus (AREA)

Abstract

本申请公开一种多节点服务器架构，涉及服务器技术领域，为了解决如何减少数据线缆的使用量及进行节点单独维护的问题，多节点服务器架构包括服务器机箱、可插拔地安装于服务器机箱内的中央处理器节点、可插拔地安装于服务器机箱内的数据交换节点、可插拔地安装于服务器机箱内的图形处理器节点、以及安装于服务器机箱内的中背板模组，中背板模组上设置有信号互联的第一连接器、第二连接器及第三连接器，中央处理器节点与第一连接器插接配合，数据交换节点与第二连接器插接配合，图形处理器节点与第三连接器插接配合。本申请能够尽量减少数据线缆的使用量，方便、快捷地进行各个节点的单独拆装维护作业，实现各节点的灵活配置，同时保证散热性能。

Description

一种多节点服务器架构
相关申请的交叉引用
本申请要求于2023年09月26日提交中国专利局，申请号为202311247520.8，申请名称为“一种多节点服务器架构”的中国专利申请的优先权，其全部内容通过引用结合在本申请中。
技术领域
本申请涉及服务器技术领域，特别涉及一种多节点服务器架构。
背景技术
服务器是电子设备中的重要组成部分，主要用于提供计算服务。根据服务器提供的服务类型不同，服务器主要分为文件服务器、存储服务器、数据库服务器、应用程序服务器、网页服务器等。
在大数据时代，大量的IT(Information Technology，信息技术)设备集中放置在数据中心。数据中心设备主要包含各类型的服务器、存储、交换机、机柜及其它基础设施。每种IT设备都是有各种硬件板卡组成，如计算模块、存储模块、机箱、散热模块等。
目前，得益于AI(Artificial Intelligence，人工智能)技术的发展，各类企业和科研机构对于算力的需求日趋增长，算力强大的人工智能服务器应运而生。人工智能服务器主要利用GPU(Graphics Processing Unit，图形处理器)节点提供计算服务，同时搭载CPU(Central Processing Unit，中央处理器)节点进行控制以及搭载Switch(数据交换)节点进行节点间的数据交换。
在现有技术中，人工智能服务器的图形处理器搭载方案主要有PCIE(Peripheral Component Interconnect Express，高速串行计算机扩展总线标准)卡和板载式图形处理器两种。在机箱内部空间相同的情况下，板载式图形处理器方案相比于PCIE卡方案，集成度更高，且空间占用相对较小，能够搭载更多图形处理器芯片，具有更高的算力密度。由于板载式图形处理器的整体尺寸较大，因此当选择板载式图形处理器方案时，人工智能服务器均为多节点架构，进而对服务器的易维护性提出了更高的要求。
然而，现有技术中的人工智能服务器，不同节点之间普遍采用数据线缆的方式进行两两节点互联，造成数据线缆的使用量较大，在服务器机箱中走线占据了大量安装空间，导致各个节点在服务器机箱中的拆装操作均比较麻烦，在进行检修维护时，需要分别对各个节点两头的数据线缆均进行插拔操作，工作量较大，导致难以对各个节点进行单独拆装维护，同时也难以对各个节点进行灵活配置，无法满足不同的用户对人工智能服务器的不同配置需求。此外，大量数据线缆占据通风面积，还会导致服务器的散热性能下降。
因此，如何尽量减少数据线缆的使用量，方便、快捷地进行各个节点的单独拆装维护作业，实现各节点的灵活配置，同时保证散热性能，是本领域技术人员面临的技术问题。
发明内容
本申请的目的是提供一种多节点服务器架构，能够尽量减少数据线缆的使用量，方便、快捷地进行各个节点的单独拆装维护作业，实现各节点的灵活配置，同时保证散热性能。
为解决上述技术问题，本申请提供一种多节点服务器架构，包括服务器机箱、可插拔地 安装于服务器机箱内的中央处理器节点、可插拔地安装于服务器机箱内的数据交换节点、可插拔地安装于服务器机箱内的图形处理器节点、以及安装于服务器机箱内的中背板模组，中背板模组上设置有信号互联的第一连接器、第二连接器及第三连接器，中央处理器节点与第一连接器插接配合，数据交换节点与第二连接器插接配合，图形处理器节点与第三连接器插接配合。
在一些具体实施例中，中央处理器节点、数据交换节点及图形处理器节点在服务器机箱内呈垂向层次分布；第一连接器、第二连接器及第三连接器在中背板模组上呈垂向层次分布。
在一些具体实施例中，还包括可插拔地安装于服务器机箱内的电源模组和散热模组，中背板模组上还设置有电源连接器和散热控制连接器，电源模组与电源连接器插接配合，散热模组与散热控制连接器插接配合。
在一些具体实施例中，散热模组包括散热风扇和风扇背板，散热风扇与风扇背板信号连接，且风扇背板与散热控制连接器插接配合。
在一些具体实施例中，服务器机箱包括位于中背板模组前侧的第一安装腔和位于中背板模组后侧的第二安装腔，中央处理器节点、数据交换节点及图形处理器节点均安装于第一安装腔内，电源模组和散热模组均安装于第二安装腔内。
在一些具体实施例中，第一安装腔内于服务器机箱的侧壁上设置有第一安装轨道组件、第二安装轨道组件及第三安装轨道组件，中央处理器节点可滑动地设置于第一安装轨道组件上，数据交换节点可滑动地设置于第二安装轨道组件上，图形处理器节点可滑动地设置于第三安装轨道组件上。
在一些具体实施例中，第一安装轨道组件、第二安装轨道组件及第三安装轨道组件三者中的部分或全部，为沿服务器机箱的深度尺寸方向延伸的导轨或沿服务器机箱的深度尺寸方向分布的多个滚轮。
在一些具体实施例中，第一安装腔内还设置有连接在服务器机箱的两侧侧壁上的安装托盘，用于支撑数据交换节点。
在一些具体实施例中，第二安装腔内于服务器机箱的侧壁上设置有多个电源仓，第二安装腔内于服务器机箱的两侧侧壁间设置有多个散热仓，电源模组呈竖直姿态可滑动地插设于电源仓内，散热模组可滑动地插设于散热仓内。
在一些具体实施例中，各散热仓的内壁上均连接有弹性挡板，用于在散热模组拔出时通过弹性复位并将对应的散热仓封闭。
在一些具体实施例中，中央处理器节点包括第一底座和设置于第一底座内的第一主板，第一主板的后端设置有第一节点连接器，第一节点连接器用于与第一连接器对接。
在一些具体实施例中，中央处理器节点还包括设置于第一底座前端的第一前窗，第一前窗的侧边设置有可旋转运动的第一操作把手。
在一些具体实施例中，数据交换节点包括第二底座和设置于第二底座内的第二主板，第二主板的后端设置有第二节点连接器，第二节点连接器用于与第二连接器对接。
在一些具体实施例中，数据交换节点还包括设置于第二底座内的功能扩展模组，第二主板的前端设置有扩展连接器，功能扩展模组与扩展连接器插接配合。
在一些具体实施例中，第二底座的外侧壁上设置有沿其深度尺寸方向延伸的第二滑轨， 第二滑轨用于与服务器机箱的侧壁上设置的第二安装轨道组件配合。
在一些具体实施例中，第二底座的侧壁前端设置有第二过渡连接板，第二过渡连接板上设置有可翻转运动的第二操作把手，以及用于与第二操作把手在预设翻转位置抵接的第二限位柱。
在一些具体实施例中，图形处理器节点包括第三底座、设置于第三底座内的第三主板，第三主板的后端设置有第三节点连接器，第三节点连接器用于与第三连接器对接。
在一些具体实施例中，图形处理器节点还包括倒扣在第三底座上的第三顶盖，第三底座的两侧均立设有矮折边，第三顶盖的两侧侧板分别与对应的矮折边形成可拆卸连接。
在一些具体实施例中，第三底座的外侧壁上设置有沿其深度尺寸方向延伸的第三滑轨，第三滑轨用于与服务器机箱的侧壁上设置的第三安装轨道组件配合。
在一些具体实施例中，第三底座的侧壁前端设置有第三过渡连接板，第三过渡连接板上设置有可翻转运动的第三操作把手，以及用于与第三操作把手在预设翻转位置抵接的第三限位柱。
在一些具体实施例中，第三底座的前端设置有第三前窗，第三操作把手上设置有与第三前窗可拆卸连接的锁定件，用于在第三操作把手未翻转时将其锁定在第三前窗上。
在一些具体实施例中，第三过渡连接板上还设置有与第三操作把手的转轴相连的弹性件，用于在锁定件被解锁时，通过弹力使第三操作把手预翻转预设角度。
在一些具体实施例中，第三顶盖的侧板外壁上凸设有可按压的锁销，服务器机箱的内侧壁上凸设有限位块，限位块用于与锁销形成抵接。
在一些具体实施例中，锁销的内端连接有弹性条，弹性条的一端与第三顶盖的侧板内壁相连，第三顶盖的侧板内壁上位于弹性条的另一端位置设置有限位板，限位板用于与弹性条的另一端形成抵接。
在一些具体实施例中，中背板模组包括连为一体的前背板和后背板，第一连接器、第二连接器及第三连接器均设置于前背板上，电源连接器和散热控制连接器均设置于后背板上。
本申请所提供的多节点服务器架构，主要包括服务器机箱、中央处理器节点、数据交换节点、图形处理器节点和中背板模组。其中，服务器机箱为本服务器架构的主体部件，主要用于安装和承载其余服务器组件。中央处理器节点安装在服务器机箱内，并与服务器机箱形成可插拔连接，即能够通过在服务器机箱内进行往复直线移动的方式实现插入安装操作与拔出拆卸操作，能够方便地进行在服务器机箱上进行拆装操作。中央处理器节点主要用于实现数据交互、全局控制等功能。图形处理器节点安装在服务器机箱内，并与服务器机箱形成可插拔连接，即能够通过在服务器机箱内进行往复直线移动的方式实现插入安装操作与拔出拆卸操作，能够方便地进行在服务器机箱上进行拆装操作。图形处理器节点主要用于进行AI图形数据计算。数据交换节点安装在服务器机箱内，并与服务器机箱形成可插拔连接，即能够通过在服务器机箱内进行往复直线移动的方式实现插入安装操作与拔出拆卸操作，能够方便地进行在服务器机箱上进行拆装操作。数据交换节点主要用于实现中央处理器节点与图形处理器节点之间的数据交互和通信，即中央处理器节点与图形处理器节点并不直接进行数据通信，而是通过数据交换节点进行间接数据通信。中背板模组也安装在服务器机箱内，主要用于实现中央处理器节点与数据交换节点之间以及图形处理器节点与数据交换节点之间的数据统一中转传递。在中背板模组上设置有第一连接器、第二连接器和第三连接器，该第一连 接器、第二连接器和第三连接器三者保持信号互联，且第一连接器主要用于与中央处理器节点形成插接配合，进而实现中央处理器节点与中背板模组之间的信号连接；第二连接器主要用于与数据交换节点形成插接配合，进而实现数据交换节点与中背板模组之间的信号连接；第三连接器主要用于与图形处理器节点形成插接配合，进而实现图形处理器节点与中背板模组之间的信号连接。
本申请的有益效果在于：由于中央处理器节点、数据交换节点及图形处理器节点均与服务器机箱形成插拔连接，且中央处理器节点、数据交换节点及图形处理器节点三者分别通过与第一连接器、第二连接器、第三连接器的插接配合同时与中背板模组形成信号连接，利用中背板模组和数据交换节点实现中央处理器节点与图形处理器节点之间的间接式数据通信，使得各节点之间基本无需使用任何数据线缆进行互联，因此，一方面能够尽量减少数据线缆的使用量，进而克服数据线缆占据通风面积的问题，保证散热性能；另一方面，中央处理器节点、数据交换节点及图形处理器节点三者能够方便地分别与第一连接器、第二连接器、第三连接器脱离，从而能够分别将中央处理器节点、数据交换节点及图形处理器节点三者单独从服务器机箱中拔出，进而能够方便、快捷地进行各个节点的单独拆装维护作业，实现各节点的灵活配置。
此外，在一些具体实施例中，图形处理器节点中的第三顶盖与矮折边连接后，整个图形处理器节点形成倒扣式结构，而搭载了GPU芯片的第三主板在装配过程中，即可直接沿垂向从上至下安装进第三底座内，并通过螺丝等紧固件进行固定，无需其他水平滑动运动或进行其余安装操作，最后再将第三顶盖倒扣在矮折边上即可完成装配；第三底座的侧壁高度较低，能够缩短安装行程，简化第三主板的安装步骤，进而能够提高产线装配生产效率，同时第三主板拆卸方便，具有更好的可维护性，并且还降低了第三主板在装配过程中出现磕碰风险的概率。
综上，本申请所提供的多节点服务器架构，能够尽量减少数据线缆的使用量，方便、快捷地进行各个节点的单独拆装维护作业，实现各节点的灵活配置，同时保证散热性能。
附图说明
为了更清楚地说明本申请的一些实施例或现有技术中的技术方案，下面将对一些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一些实施例，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。
图1为本申请所提供的一些具体实施方式的整体结构爆炸图。
图2为本申请所提供的一些具体实施方式的整体结构示意图。
图3为图2的另一视角示意图。
图4为服务器机箱的前端结构示意图。
图5为图4中去除安装托盘后的结构示意图。
图6为服务器机箱的后端结构示意图。
图7为中央处理器节点的具体结构示意图。
图8为图7的结构爆炸图。
图9为图7的局部结构放大图。
图10为数据交换节点的具体结构示意图。
图11为图10的结构爆炸图。
图12为图10的局部结构放大图。
图13为图形处理器节点的具体结构爆炸图。
图14为图形处理器节点的具体结构示意图。
图15为图14的局部结构示意图。
图16为第三底座的具体结构示意图。
图17为第三操作把手的翻转状态示意图。
图18为第三前窗的前后视角对比示意图。
图19为第三顶盖的具体结构示意图。
图20为图19的另一视角结构图。
图21为图形处理器节点的安装过程示意图。
图22为中背板模组的前后视角对比示意图。
其中，图1—图22中：
第一安装腔—a，第二安装腔—b；
服务器机箱—1，中央处理器节点—2，数据交换节点—3，图形处理器节点—4，中背板
模组—5，电源模组—6，散热模组—7；
第一安装轨道组件—11，第二安装轨道组件—12，第三安装轨道组件—13，安装托盘—
14，电源仓—15，散热仓—16，弹性挡板—17，限位块—18，顶盖板—19，搬运把手—110；
第一底座—21，第一主板—22，第一节点连接器—23，第一前窗—24，第一操作把手—
25，第一底托盘—26，第一顶盖—27；
第二底座—31，第二主板—32，第二节点连接器—33，功能扩展模组—34，扩展连接器
—35，第二滑轨—36，第二过渡连接板—37，第二操作把手—38，第二限位柱—39，第二顶盖—310，第二底托盘—311，硬盘模组—312；
第三底座—41，第三主板—42，第三节点连接器—43，第三顶盖—44，矮折边—45，第
三滑轨—46，第三过渡连接板—47，第三操作把手—48，第三限位柱—49，第三前窗—410，锁定件—411，弹性件—412，锁销—413，弹性条—414，限位板—415，第三底托盘—416，导风罩—417，定位柱—418，定位槽—419，避位孔—420，加强板—421，支撑块—422，加强筋—423，定位件—424，安装导向板—425；
第一连接器—51，第二连接器—52，第三连接器—53，电源连接器—54，散热控制连接
器—55，前背板—56，后背板—57，定位杆—58，通风孔—59；
散热风扇—71，风扇背板—72。
具体实施方式
下面将结合本申请的一些实施例中的附图，对本申请的一些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。
需要说明的时，本申请中涉及“第一”、“第二”等的描述，仅用于区别技术特征，该“第一”、“第二”等的描述仅用于描述目的，而不能理解为指示或暗示其相对重要性、优先 级或先后顺序。
请参考图1、图2，图1为本申请所提供的一些具体实施方式的整体结构示意图，图2为本申请所提供的一些具体实施方式的整体结构示意图。
在本申请所提供的一些具体实施方式中，多节点服务器架构主要包括服务器机箱1、中央处理器节点2、数据交换节点3、图形处理器节点4和中背板模组5。
其中，服务器机箱1为本服务器架构的主体部件，主要用于安装和承载其余服务器组件。
中央处理器节点2安装在服务器机箱1内，并与服务器机箱1形成可插拔连接，即能够通过在服务器机箱1内进行往复直线移动的方式实现插入安装操作与拔出拆卸操作，能够方便地进行在服务器机箱1上进行拆装操作。中央处理器节点2主要用于实现数据交互、全局控制等功能。
图形处理器节点4安装在服务器机箱1内，并与服务器机箱1形成可插拔连接，即能够通过在服务器机箱1内进行往复直线移动的方式实现插入安装操作与拔出拆卸操作，能够方便地进行在服务器机箱1上进行拆装操作。图形处理器节点4主要用于进行AI图形数据计算。
数据交换节点3安装在服务器机箱1内，并与服务器机箱1形成可插拔连接，即能够通过在服务器机箱1内进行往复直线移动的方式实现插入安装操作与拔出拆卸操作，能够方便地进行在服务器机箱1上进行拆装操作。数据交换节点3主要用于实现中央处理器节点2与图形处理器节点4之间的数据交互和通信，即中央处理器节点2与图形处理器节点4并不直接进行数据通信，而是通过数据交换节点3进行间接数据通信。
中背板模组5也安装在服务器机箱1内，主要用于实现中央处理器节点2与数据交换节点3之间以及图形处理器节点4与数据交换节点3之间的数据统一中转传递。在中背板模组5上设置有第一连接器51、第二连接器52和第三连接器53，该第一连接器51、第二连接器52和第三连接器53三者保持信号互联，且第一连接器51主要用于与中央处理器节点2形成插接配合，进而实现中央处理器节点2与中背板模组5之间的信号连接；第二连接器52主要用于与数据交换节点3形成插接配合，进而实现数据交换节点3与中背板模组5之间的信号连接；第三连接器53主要用于与图形处理器节点4形成插接配合，进而实现图形处理器节点4与中背板模组5之间的信号连接。
如此，本实施例所提供的多节点服务器架构，由于中央处理器节点2、数据交换节点3及图形处理器节点4均与服务器机箱1形成插拔连接，且中央处理器节点2、数据交换节点3及图形处理器节点4三者分别通过与第一连接器51、第二连接器52、第三连接器53的插接配合同时与中背板模组5形成信号连接，利用中背板模组5和数据交换节点3实现中央处理器节点2与图形处理器节点4之间的间接式数据通信，使得各节点之间基本无需使用任何数据线缆进行互联，因此，一方面能够尽量减少数据线缆的使用量，进而克服数据线缆占据通风面积的问题，保证散热性能；另一方面，中央处理器节点2、数据交换节点3及图形处理器节点4三者能够方便地分别与第一连接器51、第二连接器52、第三连接器53脱离，从而能够分别将中央处理器节点2、数据交换节点3及图形处理器节点4三者单独从服务器机箱1中拔出，进而能够方便、快捷地进行各个节点的单独拆装维护作业，实现各节点的灵活配置。
综上，本实施例所提供的多节点服务器架构，能够尽量减少数据线缆的使用量，方便、快捷地进行各个节点的单独拆装维护作业，实现各节点的灵活配置，同时保证散热性能。
为便于实现分别对中央处理器节点2、数据交换节点3及图形处理器节点4的插拔操作，本实施例中，中央处理器节点2、数据交换节点3及图形处理器节点4三者在服务器机箱1内具体呈垂向层次分布，即呈水平姿态并沿着高度方向分布。比如，中央处理器节点2位于上分层，数据交换节点3位于中层，而图形处理器节点4位于底层等。相应的，第一连接器51、第二连接器52及第三连接器53三者在中背板模组5上也同样地呈垂向层次分布，即沿着中背板模组5的高度方向分布，并且，第一连接器51、第二连接器52、第三连接器53三者在中背板模组5上的分布形式，与中央处理器节点2、数据交换节点3及图形处理器节点4三者在服务器机箱1内的分布形式相对应，以保证能够正确地一一对应。
当然，中央处理器节点2、数据交换节点3及图形处理器节点4三者在服务器机箱1内并不局限于呈垂向层次分布，比如呈竖直姿态沿着服务器机箱1的深度方向分布等也可以采用。
如图3所示，图3为图2的另一视角示意图。
此外，为保证供电和散热性能，本实施例中增设了电源模组6和散热模组7。其中，电源模组6安装在服务器机箱1内，并与服务器机箱1形成可插拔连接，即能够通过在服务器机箱1内进行往复直线移动的方式实现插入安装操作与拔出拆卸操作，能够方便地进行在服务器机箱1上进行拆装操作。电源模组6主要用于实现对其余服务器组件的供电。散热模组7安装在服务器机箱1内，并与服务器机箱1形成可插拔连接，即能够通过在服务器机箱1内进行往复直线移动的方式实现插入安装操作与拔出拆卸操作，能够方便地进行在服务器机箱1上进行拆装操作。散热模组7主要用于对其余服务器组件实现风冷散热。当然，散热模组7也可以通过液冷的方式对其余服务器组件进行散热。
相应的，本实施例在中背板模组5上增设了电源连接器54和散热控制连接器55。其中，电源连接器54主要用于与电源模组6形成插接配合，进而实现电源模组6与中背板模组5之间的电连接。散热控制连接器55主要用于与散热模组7形成插接配合，进而实现散热模组7与中背板模组5之间的信号连接。如此设置，不仅能够省去电源线缆，还能够进一步减少数据线缆的用量。
在关于散热模组7的一种具体实施例中，该散热模组7主要包括散热风扇71和风扇背板72。其中，散热风扇71与风扇背板72形成信号连接，而风扇背板72通过连接器与中背板模组5上的散热控制连接器55形成插接配合。如此设置，中央处理器节点2即可通过中背板模组5上的散热控制连接器55与散热风扇71形成信号连接，从而方便地控制散热风扇71的散热状态。
如图4、图5所示，图4为服务器机箱1的前端结构示意图，图5为图4中去除安装托盘14后的结构示意图。
在关于服务器机箱1的一些具体实施例中，该服务器机箱1的内部空间主要包括第一安装腔a和第二安装腔b。其中，第一安装腔a和第二安装腔b以中背板模组5为界，第一安装腔a位于中背板模组5的前侧，也是服务器机箱1的前端空间，主要用于安装中央处理器节点2、数据交换节点3及图形处理器节点4等核心部件；第二安装腔b位于中背板模组5的后，也是服务器机箱1的后端空间，主要用于安装电源模组6和散热模组7等其余辅助性服务器组件。如此设置，利用中背板模组5将服务器机箱1的内部空间划分为两部分，从而将各个核心部件与其余辅助性服务器组件分隔开来，避免产生安装干涉和散热影响。
一般的，服务器机箱1具体为6U高度，而中央处理器节点2通常占据1U高度，数据交换节 点3通常占据2U高度，图形处理器节点4通常占据3U高度。
进一步的，服务器机箱1的第一安装腔a具体包括第一节点安装腔、第二节点安装腔和第三节点安装腔。其中，第一节点安装腔主要用于安装中央处理器节点2，第二节点安装腔主要用于安装数据交换节点3，第三节点安装腔主要用于安装图形处理器节点4。一般的，第一节点安装腔位于第一安装腔a的上层区域，第二节点安装腔位于第一安装腔a的中层区域，第三节点安装腔位于第一安装腔a的下层区域，第一节点安装腔、第二节点安装腔和第三节点安装腔三者在第一安装腔a内沿垂向形成层次分布，互不影响。当然，第一节点安装腔、第二节点安装腔和第三节点安装腔三者的垂向分布形式还可以灵活调整，上下位置相对关系并不固定，比如第一节点安装腔位于第一安装腔a的中层区域，第二节点安装腔位于第一安装腔a的上层区域，第三节点安装腔位于第一安装腔a的下层区域等。并且，第一节点安装腔、第二节点安装腔和第三节点安装腔三者在第一安装腔a内并不仅限于形成垂向层次分布，比如沿着服务器机箱1的深度方向呈并列分布等也可以采用，此时，中央处理器节点2、数据交换节点3及图形处理器节点4分别沿垂向呈竖直姿态安装进第一安装腔a内。
此外，服务器机箱1的第一安装腔a并不仅限于包括第一节点安装腔、第二节点安装腔和第三节点安装腔，在节点数量更多时，第一安装腔a还可包括更多节点安装腔。
不仅如此，为便于中背板模组5在服务器机箱1内的安装，服务器机箱1的内部空间除了包括第一安装腔a和第二安装腔b之外，还包括中间安装腔(图中未示出)。具体的，该中间安装腔位于第一安装腔a与第二安装腔b之间，将两者互相间隔，主要用于安装中背板模组5。一般的，该中间安装腔的深度方向尺寸(或宽度)较窄，以便与中背板模组5的尺寸适配，且在中间安装腔的两侧侧壁上开设有沿垂向延伸的滑槽等，以使中背板模组5能够沿垂向滑动进中间安装腔内，实现中背板模组5在服务器机箱1内的滑动插拔式安装。当然，还可以在安装腔内辅以螺钉等紧固件对中背板模组5进行加固，或者还可以在安装腔内通过定位针等部件与中背板模组5上的定位孔配合实现定位。为便于实现中央处理器节点2、数据交换节点3及图形处理器节点4在服务器机箱1内的插拔拆装操作，本实施例中增设了第一安装轨道组件11、第二安装轨道组件12和第三安装轨道组件13。其中，中央处理器节点2具体设置在第一安装轨道组件11上，并与第一安装轨道组件11形成滑动连接，能够沿着第一安装轨道组件11进行滑动，进而沿着第一安装轨道组件11实现中央处理器节点2在服务器机箱1内的安装与拆卸操作。数据交换节点3具体设置在第二安装轨道组件12上，并与第二安装轨道组件12形成滑动连接，能够沿着第二安装轨道组件12进行滑动，进而沿着第二安装轨道组件12实现数据交换节点3在服务器机箱1内的安装与拆卸操作。图形处理器节点4具体设置在第三安装轨道组件13上，并与第三安装轨道组件13形成滑动连接，能够沿着第三安装轨道组件13进行滑动，进而沿着第三安装轨道组件13实现图形处理器节点4在服务器机箱1内的安装与拆卸操作。如此设置，中央处理器节点2、数据交换节点3及图形处理器节点4三者各自对应一条安装轨道，能够分别在各自的安装轨道上进行滑动运动，确保中央处理器节点2、数据交换节点3及图形处理器节点4三者的插拔拆装操作互相独立、互不影响，实现三者的单独拆装维护作业和个性化配置调整。
在关于第一安装轨道组件11、第二安装轨道组件12和第三安装轨道组件13的一种具体实施例中，第一安装轨道组件11、第二安装轨道组件12和第三安装轨道组件13具体为沿服务器机箱1的深度尺寸方向延伸的导轨，或者为沿服务器机箱1的深度尺寸方向分布的多个滚轮。 比如第一安装轨道组件11具体为上述导轨，而第二安装轨道组件12和第三安装轨道组件13具体为多个滚轮等。如此设置，当中央处理器节点2、数据交换节点3及图形处理器节点4分别安装到第一安装轨道组件11、第二安装轨道组件12和第三安装轨道组件13上时，能够确保三者在插拔运动过程中均保持水平姿态，实现稳定插拔操作；同时，当采用多个滚轮结构时，还能够通过滚动摩擦方式降低对中央处理器节点2、数据交换节点3及图形处理器节点4三者的摩擦和磨损，提高运动平顺性。
考虑到数据交换节点3通常设置在服务器机箱1内的第一安装腔a中的中间层位置，而数据交换节点3的重量较大，若仅由第二安装轨道组件12进行支撑，则可能会造成第二安装轨道组件12的形变。针对此，本实施例中增设了安装托盘14。具体的，该安装托盘14设置在服务器机箱1的第一安全腔中，具体连接服务器机箱1的两侧侧壁上，主要用于支撑安装数据交换节点3，辅助第二安装轨道组件12提高对数据交换节点3的安装稳定性，当然，安装托盘14并不干涉数据交换节点3在第二安装轨道组件12上的运动。
如图6所示，图6为服务器机箱1的后端结构示意图。
为便于实现为电源模组6和散热模组7在服务器机箱1内的插拔拆装操作，本实施例中还在服务器机箱1内增设了电源仓15和散热仓16。
其中，电源仓15设置在服务器机箱1的第二安装腔b内，具体位于服务器机箱1的侧壁上，并紧贴着服务器机箱1的侧壁呈垂向分布，一般同时设置有多个，比如3～6个等。相应的，电源模组6需以竖直姿态安装进电源仓15内，并且与电源仓15的底板形成滑动连接，能够沿着电源仓15的底板滑动进电源仓15内或从电源仓15内滑动拔出。如此设置，各个电源模组6合理利用了服务器机箱1的侧边空间，减小了服务器机箱1的中部安装空间的占用，提高了空间利用率。
散热仓16也设置在服务器机箱1的第二安装腔b内，具体位于服务器机箱1的中间区域，一般同时设置有多个，且按照一定规格沿垂向和宽度方向形成矩阵分布，比如3×4分布等。相应的，散热模组7即可安装在散热仓16内，并且与散热仓16的底板形成滑动连接，能够沿着散热仓16的底板滑动进散热仓16内或从散热仓16内滑动拔出。此外，风扇背板72也安装在服务器机箱1的第二安装腔b内，具体位于散热仓16的后方，从而使风扇背板72能够方便地与安装在散热仓16内的散热风扇71相连。一般的，一个风扇背板72同时与同一层散热仓16内的各个散热风扇71相连，比如一个风扇背板72与3个散热风扇71相连等。如此设置，通过在散热仓16内插拔散热模组7的方式控制散热模组7的数量，即可方便地调整服务器的散热性能上限。
进一步的，考虑到在调整各个节点的配置后，散热仓16内的散热模组7也可能会出现不满配的情况。针对此，本实施例还在各个散热仓16内增设了弹性挡板17。具体的，该弹性挡板17的一端与散热仓16的内壁相连，比如与散热仓16的顶壁相连，另一端朝着相对内壁延伸，比如延伸至散热仓16的底壁，且具有弹性。当散热模组7插入散热仓16内时，将抵接弹性挡板17并使其弹性形变至与散热仓16的内壁紧贴，使得弹性挡板17无法遮挡散热仓16的通风面积；而当散热模组7拔出散热仓16时，弹性挡板17在弹力作用下回弹，并将散热仓16封闭，相当于将对应的散热仓16关闭，通风面积降到零。如此设置，在将散热模组7从某个散热仓16内拔出时，原本进入该散热仓16内的冷风气流，将被弹性挡板17遮挡，从而流入附近的其余散热仓16，进而增强其余散热仓16的冷风流量，避免冷量浪费。
此外，本实施例在服务器机箱1的顶部设置了顶盖板19。具体的，该顶盖板19主要包括前上盖、中上盖和厚上盖。其中，前上盖位于各个节点区域，中上盖位于中背板模组5区域，后上盖位于电源模组6区域。同时。前上盖和后上盖通过拉钉等紧固件固定在服务器机箱1的侧壁上，中上盖通过工字钉在服务器机箱1的侧壁上进行定位后，再通过上盖锁固定在服务器机箱1的侧壁上。
不仅如此，为便于工作人员搬运整个服务器，本实施例还在服务器机箱1的侧壁上设置有搬运把手110。具体的，该搬运把手110能够进行翻转运动，并收纳在服务器机箱1的侧壁上，在需要使用时，只需将其向外翻转，即可抓握使用。
如图7、图8所示，图7为中央处理器节点2的具体结构示意图，图8为图7的结构爆炸图。
在关于中央处理器节点2的一些具体实施例中，该中央处理器节点2主要包括第一底座21和第一主板22。其中，第一底座21为中央处理器节点2的底层部件，主要用于承载其余零部件。第一主板22上安装有中央处理器、内存条、网卡等服务器组件，并且，为便于实现第一主板22与中背板模组5之间的信号连接，在第一主板22的后端位置设置有第一节点连接器23。该第一节点连接器23主要用于与中背板模组5上的第一连接器51对接，从而实现第一主板22与中背板模组5之间的信号连接。如此设置，在拆卸中央处理器节点2时，只需将第一节点连接器23从第一连接器51上拔出，即可使中央处理器节点2与中背板模组5脱离连接。
如图9所示，图9为图7的局部结构放大图。
进一步的，为便于工作人员实现对中央处理器节点2的插拔拆卸操作，本实施例中，中央处理器节点2还包括第一前窗24和第一操作把手25。其中，第一前窗24设置在第一底座21的前端位置，而第一操作把手25设置在第一前窗24的侧边位置，比如同时设置在第一前窗24的两侧，或仅设置在第一前窗24的其中一侧。具体的，该第一操作把手25与第一前窗24的侧边形成转动连接，使得第一操作把手25能够相对第一前窗24进行水平旋转运动。在正常状态下，第一操作把手25旋转至紧贴在第一前窗24的外侧面上，实现收纳，并通过手拧螺栓等紧固件进行固定；在插拔操作状态下，第一操作把手25旋转至远离第一前窗24的外侧面，并朝向第一底座21的前端，方便工作人员用手进行抓握施力，进而将整个中央处理器节点2插入服务器机箱1，或将整个中央处理器节点2从服务器机箱1中拔出。
此外，在第一底座21内还增设有第一底托盘26，用于支撑安装第一主板22。在第一前窗24上还可开设多个散热孔，以加强通风散热。在第一底座21的顶部还设置有第一顶盖27，该第一顶盖27通过工字钉等部件卡入第一底座21的侧壁顶部槽位进行定位后再通过按压式上盖锁与第一底座21固定。在第一主板22的后端还开设有连接器定位孔，以与中背板模组5上设置的定位柱418进行定位配合。在第一底座21的后端还开设有定位缺口，以与服务器机箱1内部设置的工字钉等部件形成定位配合，进而实现整个中央处理器节点2在服务器机箱1内的安装定位。
如图10、图11所示，图10为数据交换节点3的具体结构示意图，图11为图10的结构爆炸图。
在关于数据交换节点3的一些具体实施例中，该数据交换节点3主要包括第二底座31和第二主板32。其中，第二底座31为数据交换节点3的底层部件，主要用于承载其余零部件。第二主板32上安装有数据处理模组等服务器组件，并且，为便于实现第二主板32与中背板模组5之间的信号连接，在第二主板32的后端位置设置有第二节点连接器33。该第二节点连接器 33主要用于与中背板模组5上的第二连接器52对接，从而实现第二主板32与中背板模组5之间的信号连接。如此设置，在拆卸数据交换节点3时，只需将第二节点连接器33从第二连接器52上拔出，即可使数据交换节点3与中背板模组5脱离连接。
为提高服务器的扩展性能，本实施例在数据交换节点3中增设了功能扩展模组34。其中，该功能扩展模组34设置在第二底座31内，比如设置在第二底座31的前端位置，具体可为PCIE模组或其余类型的扩展模组，比如能够安装搭载GPU芯片的PCIE卡或者搭载网络芯片的PCIE卡等。一般的，功能扩展模组34具体设置在第二底座31的前端位置，而第二主板32具体设置在第二底座31的后端位置。同时，为便于实现功能扩展模组34与第二主板32之间的信号连接，本实施例还在第二主板32的前端设置有扩展连接器35。具体的，该扩展连接器35主要用于与功能扩展模组34上的连接器形成插接配合，从而实现功能扩展模组34与第二主板32之间的信号连接，并且方便功能扩展模组34与第二主板32之间的拆装操作，进而实现灵活配置。
为便于实现数据交换节点3在第二安装轨道组件12上的滑动插拔运动，本实施例中增设了第二滑轨36。具体的，该第二滑轨36设置在第二底座31的外侧壁上，可以仅单侧设置，也可以两侧同时设置，具体沿着第二底座31的深度尺寸方向(通常为长度方向)延伸预设长度，主要用于与服务器机箱1的侧壁上设置的第二安装轨道组件12配合。如此设置，通过第二滑轨36与第二安装轨道组件12的配合，即可在对数据交换节点3进行插拔操作时，使得第二滑轨36沿着第二安装轨道组件12进行滑动，从而对数据交换节点3的插拔运动实现导向作用。比如，当第二安装轨道组件12具体采用多个滚轮时，第二滑轨36即可同时与各个滚轮形成滚动摩擦。
如图12所示，图12为图10的局部结构放大图。
为便于工作人员实现对数据交换节点3的插拔拆装操作，本实施例中增设了第二过渡连接板37和第二操作把手38。其中，第二过渡连接板37设置在第二底座31的侧壁前端位置，比如同时设置在第二底座31的两侧，或仅设置在第二底座31的其中一侧。第二操作把手38设置在第二过渡连接板37上，并与第二过渡连接板37之间形成转动连接，能够相对第二过渡连接板37进行翻转运动。在正常状态下，第二操作把手38翻转至竖直姿态，并收纳于第二过渡连接板37的外侧面上，同时还可通过手拧螺栓等紧固件进行固定；在插拔操作状态下，第二操作把手38向外翻转至远离第二过渡连接板37，并呈预设倾角姿态，且整体朝向第二底座31的前方，方便工作人员用手进行抓握施力，进而将整个数据交换节点3插入服务器机箱1，或将整个数据交换节点3从服务器机箱1中拔出。
进一步的，考虑到第二操作把手38的翻转角度不宜过大，针对此，本实施例中增设了第二限位柱39。具体的，该第二限位柱39设置在第二过渡连接板37上，具体位于第二操作把手38的后方区域，主要用于在第二操作把手38向外翻转至预设角度时，对第二操作把手38的后端形成抵接，使得第二操作把手38无法进行向外翻转，从而限制第二操作把手38的最大外翻角度。一般的，第二操作把手38的最大外翻角度可在30～60°之间。
此外，本实施例还在第二底座31的侧壁上开设有散热孔，在第二底座31内还设置有导风罩，以加强通风散热性能。同时，在第二底座31的后端设置有加强横梁，以提高结构强度。在第二底座31的顶部设置有第二顶盖310，该第二顶盖310通过工字钉等部件与第二底座31的侧壁顶部上的对应槽位进行定位配合，再通过上盖锁将第二顶盖310固定在第二底座31上。 在第二底座31内还设置有第二底托盘311，以对第二主板32进行支撑安装。在第二底座31的前端还可设置硬盘模组312，该硬盘模组312一般难可以安装4～8个竖插的2.5寸硬盘，硬盘插接硬盘背板后再通过数据线缆连接第二主板32。
如图13、图14、图15所示，图13为图形处理器节点4的具体结构爆炸图，图14为图形处理器节点4的具体结构示意图，图15为图14的局部结构示意图。
在关于图形处理器节点4的一些具体实施例中，该图形处理器节点4主要包括第三底座41和第三主板42。其中，第三底座41为图形处理器节点4的底层部件，主要用于承载其余零部件。第三主板42上安装有GPU芯片等服务器组件，并且，为便于实现第三主板42与中背板模组5之间的信号连接，在第三主板42的后端位置设置有第三节点连接器43。该第三节点连接器43主要用于与中背板模组5上的第三连接器53对接，从而实现第三主板42与中背板模组5之间的信号连接。如此设置，在拆卸图形处理器节点4时，只需将第三节点连接器43从第三连接器53上拔出，即可使图形处理器节点4与中背板模组5脱离连接。
如图16、图21所示，图16为第三底座41的具体结构示意图，图21为图形处理器节点4的安装过程示意图。
考虑到在现有技术中，安装有GPU芯片的GPU主板的尺寸较大，导致在GPU主板的装配过程需要使用专用的治具完成多步平移工序，GPU板的安装过程比较麻烦，限制了图形处理器节点4的生产效率，且装配过程工序越多，因工人操作问题造成GPU主板与机箱磕碰问题的概率越高。针对此，为解决GPU主板在装配过程中因装配工序较多而影响产线装配效率的问题，本实施例在图形处理器节点4中增设了第三顶盖44和矮折边45。其中，第三顶盖44与前述第一顶盖2719、第二顶盖310类似，为第三底座41的盖体结构，但不同的是，该第三顶盖44的两侧侧板的高度较大，且明显大于矮折边45的高度，能够倒扣在第三底座41上进行安装。矮折边45立设在第三底座41的两侧侧边位置，其高度较低，相当于第三底座41的两侧翻折边，使得第三底座41更接近于平板状或盘状。同时，第三顶盖44的两侧侧板分别与两侧的矮折边45形成可拆卸连接。如此设置，第三顶盖44与矮折边45连接后，整个图形处理器节点4形成倒扣式结构，而搭载了GPU芯片的第三主板42在装配过程中，即可直接沿垂向从上至下安装进第三底座41内，并通过螺丝等紧固件进行固定，无需其他水平滑动运动或进行其余安装操作，最后再将第三顶盖44倒扣在矮折边45上即可完成装配；第三底座41的侧壁高度较低，能够缩短安装行程，简化第三主板42的安装步骤，进而能够提高产线装配生产效率，同时第三主板42拆卸方便，具有更好的可维护性，并且还降低了第三主板在装配过程中出现磕碰风险的概率。
进一步的，为便于实现第三顶盖44与矮折边45之间的可拆卸连接，本实施例中，在矮折边45的顶部开设有定位槽419，同时在第三顶盖44的底部设置有工字钉等部件，以与定位槽419进行配合实现安装定位。同时，在矮折边45的侧壁上还开设有多个螺纹孔，以与第三顶盖44的两侧侧板形成螺纹连接。
为便于实现图形处理器节点4在第三安装轨道组件13上的滑动插拔运动，本实施例中增设了第三滑轨46。具体的，该第三滑轨46设置在第三底座41的外侧壁上，可以仅单侧设置，也可以两侧同时设置，具体沿着第三底座41的深度尺寸方向(通常为长度方向)延伸预设长度，主要用于与服务器机箱1的侧壁上设置的第三安装轨道组件13配合。如此设置，通过第三滑轨46与第三安装轨道组件13的配合，即可在对图形处理器节点4进行插拔操作时，使得 第三滑轨46沿着第三安装轨道组件13进行滑动，从而对图形处理器节点4的插拔运动实现导向作用。比如，当第三安装轨道组件13具体采用多个滚轮时，第三滑轨46即可同时与各个滚轮形成滚动摩擦。
如图17所示，图17为第三操作把手48的翻转状态示意图。
为便于工作人员实现对图形处理器节点4的插拔拆装操作，本实施例中增设了第三过渡连接板47和第三操作把手48。其中，第三过渡连接板47设置在第三底座41的侧壁前端位置，比如同时设置在第三底座41的两侧，或仅设置在第三底座41的其中一侧。该第三过渡连接板47同时用于实现第三前窗410在第三底座41前端的安装。第三操作把手48设置在第三过渡连接板47上，并与第三过渡连接板47之间形成转动连接，能够相对第三过渡连接板47进行翻转运动。在正常状态下，第三操作把手48翻转至竖直姿态，并收纳于第三过渡连接板47的外侧面上，同时还可通过手拧螺栓等锁定件411进行固定；在插拔操作状态下，第三操作把手48向外翻转至远离第三过渡连接板47，并呈预设倾角姿态，且整体朝向第三底座41的前方，方便工作人员用手进行抓握施力，进而将整个图形处理器节点4插入服务器机箱1，或将整个图形处理器节点4从服务器机箱1中拔出。
进一步的，考虑到第三操作把手48的翻转角度不宜过大，针对此，本实施例中增设了第三限位柱49。具体的，该第三限位柱49设置在第三过渡连接板47上，具体位于第三操作把手48的后方区域，主要用于在第三操作把手48向外翻转至预设角度时，对第三操作把手48的后端形成抵接，使得第三操作把手48无法进行向外翻转，从而限制第三操作把手48的最大外翻角度。一般的，第三操作把手48的最大外翻角度可在30～60°之间。
更进一步的，本实施例中还增设有弹性件412。具体的，该弹性件412的一端连接在第三操作把手48的转轴上，另一端连接在第三过渡连接板47的外侧壁上，当第三操作把手48向内翻转至收纳状态时，弹性件412被压缩，并蓄积弹性势能，同时由于锁定件411将第三操作把手48锁定在收纳状态，因此弹性件412能够保持在压缩状态；而当锁定件411被工作人员解锁时，弹性件412立即回弹，释放弹性势能，并驱动第三操作把手48向外翻转，即通过弹力驱动第三操作把手48自动预翻转预设角度，从而方便工作人员进行抓握，无需再从收纳状态一直将第三操作把手48向外翻转，不仅节省力气，而且还提高了操作效率。
如图19、图20所示，图19为第三顶盖44的具体结构示意图，图20为图19的另一视角结构图。
此外，考虑到图形处理器节点4的重量较大，在将图形处理器节点4向外拔出拆卸的过程中，若工作人员不注意力道控制，则可能在图形处理器节点4的惯性作用下而直接从第三底座41中跌落，导致损坏。针对此，本实施例中增设了锁销413和限位块18。具体的，该锁销413设置在第三顶盖44的侧板外壁上，可以同时设置在第三顶盖44的两侧侧板上，也可以仅设置在第三顶盖44的其中一侧侧板上。同时，该锁销413凸出第三顶盖44的侧板外壁，并且能够供工作人员进行按压操作。相应的，限位块18具体设置在服务器机箱1的内侧壁上，并凸出服务器机箱1的内侧壁，主要用于对锁销413形成抵接。如此设置，工作人员在将图形处理器节点4拉出服务器机箱1时，无法直接将图形处理器节点4拉出至第三底座41外，而是在中途会由于限位块18对锁销413形成抵接而被迫暂停，只有在工作人员对锁销413进行按压解锁后，才能继续将图形处理器节点4向外拉出，从而有效防止图形处理器节点4出现意外坠落事故。
进一步的，为防止工作人员将锁销413按压得过深而导致失效，本实施例中增设了弹性条414和限位板415。其中，弹性条414设置在锁销413的内端，且锁销413的一端与第三顶盖44的侧板内壁相连，而锁销413的另一端沿着第三顶盖44的侧板的长度方向延伸。当锁销413被按压时，弹性条414随之一同弹性形变而朝内侧产生偏转。限位板415设置在第三顶盖44的侧板内壁上，具体位于弹性条414的另一端位置，主要用于对弹性条414的另一端形成抵接，限制弹性条414的最大偏转偏转，进而防止锁销413被工作人员按压得过深。
此外，本实施例还在第三底座41内设置有第三底托盘416，以对第三主板42进行支撑安装。同时，在第三底托盘416上开设有多个葫芦孔，在第三底座41的底面上设置有多个定位柱418，通过各个葫芦孔与各个定位柱418的配合，实现第三底托盘416在第三底座41上的定位安装。在矮折边45的顶部开设有定位槽419，同时在第三顶盖44的底部设置有工字钉等定位件424，以通过定位槽419与定位件424的配合实现第三顶盖44在第三底座41上的定位安装。为提高散热性能，在第三底座41内增设有导风罩417。同时，在矮折边45的顶部还开设有用于安装导风罩417的搭接安装槽位，以及用于避位弹性条414和限位板415的避位孔420。在第三底座41的前端与第三过渡连接板47相连的位置处，通过将矮折边45的局部区域加高的方式形成L型加强板421，以提高连接强度。在第三底座41的后端开设有定位缺口以实现在服务器机箱1内的定位安装，并且在第三底座41的后端还设置有安装导向板425，该安装导向板425呈倾斜状，主要用于在安装图形处理器节点4，通过安装导向板425与服务器机箱1的抵接，对第三底座41的安装运动形成导向作用，从而更加顺利地安装进服务器机箱1内。
如图18所示，图18为第三前窗410的前后视角对比示意图。
不仅如此，本实施例还在第三前窗410上开设有多个散热孔，以强化通风散热性能。同时，还在第三前窗410的顶部设置有支撑块422，以支撑第三顶盖44的前端，防止第三顶盖44的前端下沉。为提高第三前窗410的结构强度，本实施例还在第三前窗410的内侧壁上设置有多根加强筋423。
如图22所示，图22为中背板模组5的前后视角对比示意图。
在关于中背板模组5的一些具体实施例中，该中背板模组5主要包括前背板56和后背板57。其中，前背板56与后背板57连为一体，且前背板56朝向服务器机箱1的前方，而后背板57朝向服务器机箱1的后方。同时，第一连接器51、第二连接器52及第三连接器53均设置在前背板56上，而电源连接器54和散热控制连接器55均设置于后背板57上。如此设置，通过前背板56与后背板57分别将第一连接器51、第二连接器52及第三连接器53，以及电源连接器54和散热控制连接器55互相隔离，能够避免热量集中现象和连接混淆现象。
此外，在前背板56与后背板57上可均开设多个通风孔59，以强化通风散热性能。并且，考虑到第一节点连接器23、第二节点连接器33、第三节点连接器43分别需要与前背板56上的第一连接器51、第二连接器52及第三连接器53对接，且电源模组6、散热模组7分别需要与后背板57上的及电源连接器54、散热控制连接器55对接，为保证对接精确，本实施例还在前背板56和后背板57上设置了多个定位杆58，以通过定位杆58与各个节点上的连接器上或电源模组6、散热模组7上的定位沉孔等部件形成定位配合。
对所公开的实施例的上述说明，使本领域专业技术人员能够实现或使用本申请。对这些实施例的多种修改对本领域的专业技术人员来说将是显而易见的，本文中所定义的一般原理可以在不脱离本申请的精神或范围的情况下，在其它实施例中实现。因此，本申请将不会被 限制于本文所示的这些实施例，而是要符合与本文所公开的原理和新颖特点相一致的最宽的范围。

Claims (25)

  1. 一种多节点服务器架构，其特征在于，包括服务器机箱(1)、可插拔地安装于所述服务器机箱(1)内的中央处理器节点(2)、可插拔地安装于所述服务器机箱(1)内的数据交换节点(3)、可插拔地安装于所述服务器机箱(1)内的图形处理器节点(4)、以及安装于所述服务器机箱(1)内的中背板模组(5)，所述中背板模组(5)上设置有信号互联的第一连接器(51)、第二连接器(52)及第三连接器(53)，所述中央处理器节点(2)与所述第一连接器(51)插接配合，所述数据交换节点(3)与所述第二连接器(52)插接配合，所述图形处理器节点(4)与所述第三连接器(53)插接配合。
  2. 根据权利要求1所述的多节点服务器架构，其特征在于，所述中央处理器节点(2)、所述数据交换节点(3)及所述图形处理器节点(4)在所述服务器机箱(1)内呈垂向层次分布；所述第一连接器(51)、第二连接器(52)及第三连接器(53)在所述中背板模组(5)上呈垂向层次分布。
  3. 根据权利要求1所述的多节点服务器架构，其特征在于，还包括可插拔地安装于所述服务器机箱(1)内的电源模组(6)和散热模组(7)，所述中背板模组(5)上还设置有电源连接器(54)和散热控制连接器(55)，所述电源模组(6)与所述电源连接器(54)插接配合，所述散热模组(7)与所述散热控制连接器(55)插接配合。
  4. 根据权利要求3所述的多节点服务器架构，其特征在于，所述散热模组(7)包括散热风扇(71)和风扇背板(72)，所述散热风扇(71)与所述风扇背板(72)信号连接，且所述风扇背板(72)与所述散热控制连接器(55)插接配合。
  5. 根据权利要求3所述的多节点服务器架构，其特征在于，所述服务器机箱(1)包括位于所述中背板模组(5)前侧的第一安装腔(a)和位于所述中背板模组(5)后侧的第二安装腔(b)，所述中央处理器节点(2)、所述数据交换节点(3)及所述图形处理器节点(4)均安装于所述第一安装腔(a)内，所述电源模组(6)和所述散热模组(7)均安装于所述第二安装腔(b)内。
  6. 根据权利要求5所述的多节点服务器架构，其特征在于，所述第一安装腔(a)内于所述服务器机箱(1)的侧壁上设置有第一安装轨道组件(11)、第二安装轨道组件(12)及第三安装轨道组件(13)，所述中央处理器节点(2)可滑动地设置于所述第一安装轨道组件(11)上，所述数据交换节点(3)可滑动地设置于所述第二安装轨道组件(12)上，所述图形处理器节点(4)可滑动地设置于所述第三安装轨道组件(13)上。
  7. 根据权利要求6所述的多节点服务器架构，其特征在于，所述第一安装轨道组件(11)、第二安装轨道组件(12)及第三安装轨道组件(13)三者中的部分或全部，为沿所述服务器机箱(1)的深度尺寸方向延伸的导轨或包括沿所述服务器机箱(1)的深度尺寸方向分布的多个滚轮。
  8. 根据权利要求6所述的多节点服务器架构，其特征在于，所述第一安装腔(a)内还设置有连接在所述服务器机箱(1)的两侧侧壁上的安装托盘(14)，用于支撑所述数据交换节点(3)。
  9. 根据权利要求5所述的多节点服务器架构，其特征在于，所述第二安装腔(b)内于所述服务器机箱(1)的侧壁上设置有多个电源仓(15)，所述第二安装腔(b)内于所述服务器机箱(1)的两侧侧壁间设置有多个散热仓(16)，所述电源模组(6)呈竖直姿态可滑动地插设于所述电源仓(15)内，所述散热模组(7)可滑动地插设于所述散热仓(16)内。
  10. 根据权利要求9所述的多节点服务器架构，其特征在于，各所述散热仓(16)的内壁上均连接有弹性挡板(17)，用于在所述散热模组(7)拔出时通过弹性复位并将对应的所述散热仓(16)封闭。
  11. 根据权利要求1所述的多节点服务器架构，其特征在于，所述中央处理器节点(2)包括第一底座(21)和设置于所述第一底座(21)内的第一主板(22)，所述第一主板(22)的后端设置有第一节点连接器(23)，所述第一节点连接器(23)用于与所述第一连接器(51)对接。
  12. 根据权利要求11所述的多节点服务器架构，其特征在于，所述中央处理器节点(2)还包括设置于所述第一底座(21)前端的第一前窗(24)，所述第一前窗(24)的侧边设置有可旋转运动的第一操作把手(25)。
  13. 根据权利要求1所述的多节点服务器架构，其特征在于，所述数据交换节点(3)包括第二底座(31)和设置于所述第二底座(31)内的第二主板(32)，所述第二主板(32)的后端设置有第二节点连接器(33)，所述第二节点连接器(33)用于与所述第二连接器(52)对接。
  14. 根据权利要求13所述的多节点服务器架构，其特征在于，所述数据交换节点(3)还包括设置于所述第二底座(31)内的功能扩展模组(34)，所述第二主板(32)的前端设置有扩展连接器(35)，所述功能扩展模组(34)与所述扩展连接器(35)插接配合。
  15. 根据权利要求13所述的多节点服务器架构，其特征在于，所述第二底座(31)的外侧壁上设置有沿其深度尺寸方向延伸的第二滑轨(36)，所述第二滑轨(36)用于与所述服务器机箱(1)的侧壁上设置的第二安装轨道组件(12)配合。
  16. 根据权利要求13所述的多节点服务器架构，其特征在于，所述第二底座(31)的侧壁前端设置有第二过渡连接板(37)，所述第二过渡连接板(37)上设置有可翻转运动的第二操作把手(38)，以及用于与所述第二操作把手(38)在预设翻转位置抵接的第二限位柱(39)。
  17. 根据权利要求1-16任一项所述的多节点服务器架构，其特征在于，所述图形处理器节点(4)包括第三底座(41)、设置于所述第三底座(41)内的第三主板(42)，所述第三主板(42)的后端设置有第三节点连接器(43)，所述第三节点连接器(43)用于与所述第三连接器(53)对接。
  18. 根据权利要求17所述的多节点服务器架构，其特征在于，所述图形处理器节点(4)还包括倒扣在所述第三底座(41)上的第三顶盖(44)，所述第三底座(41)的两侧均立设有矮折边(45)，所述第三顶盖(44)的两侧侧板分别与对应的所述矮折边(45)形成可拆卸连接。
  19. 根据权利要求17所述的多节点服务器架构，其特征在于，所述第三底座(41)的外侧壁上设置有沿其深度尺寸方向延伸的第三滑轨(46)，所述第三滑轨 (46)用于与所述服务器机箱(1)的侧壁上设置的第三安装轨道组件(13)配合。
  20. 根据权利要求17所述的多节点服务器架构，其特征在于，所述第三底座(41)的侧壁前端设置有第三过渡连接板(47)，所述第三过渡连接板(47)上设置有可翻转运动的第三操作把手(48)，以及用于与所述第三操作把手(48)在预设翻转位置抵接的第三限位柱(49)。
  21. 根据权利要求20所述的多节点服务器架构，其特征在于，所述第三底座(41)的前端设置有第三前窗(410)，所述第三操作把手(48)上设置有与所述第三前窗(410)可拆卸连接的锁定件(411)，用于在所述第三操作把手(48)未翻转时将其锁定在所述第三前窗(410)上。
  22. 根据权利要求21所述的多节点服务器架构，其特征在于，所述第三过渡连接板(47)上还设置有与所述第三操作把手(48)的转轴相连的弹性件(412)，用于在所述锁定件(411)被解锁时，通过弹力使所述第三操作把手(48)预翻转预设角度。
  23. 根据权利要求18所述的多节点服务器架构，其特征在于，所述第三顶盖(44)的侧板外壁上凸设有可按压的锁销(413)，所述服务器机箱(1)的内侧壁上凸设有限位块(18)，所述限位块(18)用于与所述锁销(413)形成抵接。
  24. 根据权利要求23所述的多节点服务器架构，其特征在于，所述锁销(413)的内端连接有弹性条(414)，所述弹性条(414)的一端与所述第三顶盖(44)的侧板内壁相连，所述第三顶盖(44)的侧板内壁上位于所述弹性条(414)的另一端位置设置有限位板(415)，所述限位板(415)用于与所述弹性条(414)的另一端形成抵接。
  25. 根据权利要求3所述的多节点服务器架构，其特征在于，所述中背板模组(5)包括连为一体的前背板(56)和后背板(57)，所述第一连接器(51)、所述第二连接器(52)及所述第三连接器(53)均设置于所述前背板(56)上，所述电源连接器(54)和所述散热控制连接器(55)均设置于所述后背板(57)上。
PCT/CN2024/089401 2023-09-26 2024-04-23 一种多节点服务器架构 Pending WO2025066122A1 (zh)

Priority Applications (1)

Application Number Priority Date Filing Date Title
EP24869691.6A EP4600837A4 (en) 2023-09-26 2024-04-23 MULTI-NODE SERVER ARCHITECTURE

Applications Claiming Priority (2)

Application Number Priority Date Filing Date Title
CN202311247520.8A CN116991783B (zh) 2023-09-26 2023-09-26 一种多节点服务器架构
CN202311247520.8 2023-09-26

Publications (1)

Publication Number Publication Date
WO2025066122A1 true WO2025066122A1 (zh) 2025-04-03

Family

ID=88532505

Family Applications (1)

Application Number Title Priority Date Filing Date
PCT/CN2024/089401 Pending WO2025066122A1 (zh) 2023-09-26 2024-04-23 一种多节点服务器架构

Country Status (3)

Country Link
EP (1) EP4600837A4 (zh)
CN (1) CN116991783B (zh)
WO (1) WO2025066122A1 (zh)

Cited By (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN120469549A (zh) * 2025-07-14 2025-08-12 苏州元脑智能科技有限公司 电源模块安装支架、电源供应单元及服务器
CN120994024A (zh) * 2025-10-22 2025-11-21 浪潮电子信息产业股份有限公司 一种机箱和电子设备

Families Citing this family (8)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN116991783B (zh) * 2023-09-26 2024-02-09 苏州元脑智能科技有限公司 一种多节点服务器架构
TW202520089A (zh) * 2023-11-09 2025-05-16 和碩聯合科技股份有限公司 多節點式伺服器
CN117270651A (zh) * 2023-11-22 2023-12-22 联宝(合肥)电子科技有限公司 一种支持多gpu卡的服务器
CN117666730B (zh) * 2024-01-30 2024-05-24 苏州元脑智能科技有限公司 服务器
CN223245103U (zh) * 2024-09-25 2025-08-19 超聚变数字技术有限公司 计算节点和计算设备
CN119719004B (zh) * 2025-02-27 2025-07-11 苏州元脑智能科技有限公司 一种服务器
CN120353308B (zh) * 2025-06-24 2025-09-23 苏州元脑智能科技有限公司 服务器
CN120371094B (zh) * 2025-06-26 2025-09-16 苏州元脑智能科技有限公司 服务器架构

Citations (9)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN2763872Y (zh) * 2004-10-30 2006-03-08 鸿富锦精密工业（深圳）有限公司 电脑盖板锁固装置
CN102279633A (zh) * 2011-08-26 2011-12-14 华为技术有限公司 服务器
CN202421958U (zh) * 2011-12-31 2012-09-05 曙光信息产业股份有限公司 服务器
EP2785166A2 (en) * 2013-03-27 2014-10-01 Quanta Computer, Inc Server rack and its server device
CN109710557A (zh) * 2018-12-14 2019-05-03 郑州云海信息技术有限公司 一种支持16gpu的服务器结构
CN209821735U (zh) * 2019-04-12 2019-12-20 深圳市国鑫恒宇科技有限公司 一种4u8节点的可扩展计算型服务器
US20230069162A1 (en) * 2021-08-31 2023-03-02 SQ Technology (Shanghai) Corporation Server and chassis thereof
CN116010086A (zh) * 2022-12-21 2023-04-25 硅基大陆(成都)科技有限公司 多节点架构的装置和机架
CN116991783A (zh) * 2023-09-26 2023-11-03 苏州元脑智能科技有限公司 一种多节点服务器架构

Family Cites Families (8)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US7408772B2 (en) * 2004-05-14 2008-08-05 Hewlett-Packard Development Company, L.P. Fan tray electronics enclosure
US7577134B2 (en) * 2005-08-19 2009-08-18 Brocade Communications Systems, Inc. Port expander for fibre channel fabrics in storage area networks
CN206235994U (zh) * 2016-12-13 2017-06-09 北京天地超云科技有限公司 一种用于4u机箱多节点服务器的后置散热结构
CN110781057A (zh) * 2019-10-25 2020-02-11 湖南工业职业技术学院 一种用于融合架构服务器的管理系统
CN113609062B (zh) * 2021-07-12 2024-05-07 深圳市国鑫恒运信息安全有限公司 一种通过背板互联的4u无线缆化服务器
CN218512885U (zh) * 2022-07-11 2023-02-21 云尖信息技术有限公司 服务器
CN115794381A (zh) * 2022-11-09 2023-03-14 阿里巴巴（中国）有限公司 一种服务器和数据中心
CN116700445A (zh) * 2023-06-01 2023-09-05 深圳市瑞驰信息技术有限公司 一种基于分布式存储硬件架构的全闪存arm存储服务器

Patent Citations (9)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN2763872Y (zh) * 2004-10-30 2006-03-08 鸿富锦精密工业（深圳）有限公司 电脑盖板锁固装置
CN102279633A (zh) * 2011-08-26 2011-12-14 华为技术有限公司 服务器
CN202421958U (zh) * 2011-12-31 2012-09-05 曙光信息产业股份有限公司 服务器
EP2785166A2 (en) * 2013-03-27 2014-10-01 Quanta Computer, Inc Server rack and its server device
CN109710557A (zh) * 2018-12-14 2019-05-03 郑州云海信息技术有限公司 一种支持16gpu的服务器结构
CN209821735U (zh) * 2019-04-12 2019-12-20 深圳市国鑫恒宇科技有限公司 一种4u8节点的可扩展计算型服务器
US20230069162A1 (en) * 2021-08-31 2023-03-02 SQ Technology (Shanghai) Corporation Server and chassis thereof
CN116010086A (zh) * 2022-12-21 2023-04-25 硅基大陆(成都)科技有限公司 多节点架构的装置和机架
CN116991783A (zh) * 2023-09-26 2023-11-03 苏州元脑智能科技有限公司 一种多节点服务器架构

Non-Patent Citations (1)

* Cited by examiner, † Cited by third party
Title
See also references of EP4600837A4 *

Cited By (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN120469549A (zh) * 2025-07-14 2025-08-12 苏州元脑智能科技有限公司 电源模块安装支架、电源供应单元及服务器
CN120994024A (zh) * 2025-10-22 2025-11-21 浪潮电子信息产业股份有限公司 一种机箱和电子设备

Also Published As

Publication number Publication date
EP4600837A1 (en) 2025-08-13
CN116991783B (zh) 2024-02-09
EP4600837A4 (en) 2026-03-11
CN116991783A (zh) 2023-11-03

Similar Documents

Publication Publication Date Title
EP4600837A1 (en) Multi-node server architecture
US7453707B2 (en) Tool-less, translating hard drive bay
US7298612B2 (en) Server with vertical drive arrangement
US8897017B2 (en) Serviceable hard disk drive trays for a server rack
US6490153B1 (en) Computer system for highly-dense mounting of system components
US7068498B2 (en) Computer system with slidable motherboard
CN205540468U (zh) 电子装置及其应用的辅助装置
CN108919900A (zh) 一种服务器系统
WO2012089128A1 (zh) 服务器、服务器组件及控制风扇转速方法
CN106292913A (zh) 服务器
CN101639712A (zh) 服务器
CN102193589A (zh) 服务器辅助运算系统
US12555615B2 (en) Storage server
US7136283B2 (en) Multi-computer system
US7576977B2 (en) Shoulder screw and handle drive mounting system
CN221551170U (zh) 一种服务器
CN109976465A (zh) 服务器
CN113609062A (zh) 一种通过背板互联的4u无线缆化服务器
CN118260234A (zh) 服务器
CN115793810A (zh) 服务器及机柜
CN217847037U (zh) 一种服务器
CN100399229C (zh) 滑动式平面显示器与键盘模块
US9508392B2 (en) Systems and methods for mechanical isolation of information handling resources
JP3253348U (ja) 産業用コンピュータケースの構造改良
US20170285696A1 (en) Method and Apparatus for Mounting Power Supplies in Rack-Mountable Computer Chassis

Legal Events

Date Code Title Description
WWE Wipo information: entry into national phase

Ref document number: 2024869691

Country of ref document: EP

ENP Entry into the national phase

Ref document number: 2024869691

Country of ref document: EP

Effective date: 20250507

121 Ep: the epo has been informed by wipo that ep was designated in this application

Ref document number: 24869691

Country of ref document: EP

Kind code of ref document: A1

WWP Wipo information: published in national office

Ref document number: 2024869691

Country of ref document: EP