WO2024045735A1 - 计算节点及计算设备 - Google Patents

计算节点及计算设备 Download PDF

Info

Publication number
WO2024045735A1
WO2024045735A1 PCT/CN2023/098055 CN2023098055W WO2024045735A1 WO 2024045735 A1 WO2024045735 A1 WO 2024045735A1 CN 2023098055 W CN2023098055 W CN 2023098055W WO 2024045735 A1 WO2024045735 A1 WO 2024045735A1
Authority
WO
WIPO (PCT)
Prior art keywords
layer
main board
current
hole
motherboard
Prior art date
Application number
PCT/CN2023/098055
Other languages
English (en)
French (fr)
Other versions
WO2024045735A9 (zh
Inventor
刘国强
姬忠礼
Original Assignee
超聚变数字技术有限公司
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 超聚变数字技术有限公司 filed Critical 超聚变数字技术有限公司
Publication of WO2024045735A1 publication Critical patent/WO2024045735A1/zh
Publication of WO2024045735A9 publication Critical patent/WO2024045735A9/zh

Links

Classifications

    • H—ELECTRICITY
    • H05—ELECTRIC TECHNIQUES NOT OTHERWISE PROVIDED FOR
    • H05K—PRINTED CIRCUITS; CASINGS OR CONSTRUCTIONAL DETAILS OF ELECTRIC APPARATUS; MANUFACTURE OF ASSEMBLAGES OF ELECTRICAL COMPONENTS
    • H05K1/00—Printed circuits
    • H05K1/18—Printed circuits structurally associated with non-printed electric components
    • H—ELECTRICITY
    • H01—ELECTRIC ELEMENTS
    • H01B—CABLES; CONDUCTORS; INSULATORS; SELECTION OF MATERIALS FOR THEIR CONDUCTIVE, INSULATING OR DIELECTRIC PROPERTIES
    • H01B5/00—Non-insulated conductors or conductive bodies characterised by their form
    • H01B5/02—Single bars, rods, wires, or strips
    • H—ELECTRICITY
    • H05—ELECTRIC TECHNIQUES NOT OTHERWISE PROVIDED FOR
    • H05K—PRINTED CIRCUITS; CASINGS OR CONSTRUCTIONAL DETAILS OF ELECTRIC APPARATUS; MANUFACTURE OF ASSEMBLAGES OF ELECTRICAL COMPONENTS
    • H05K1/00—Printed circuits
    • H05K1/02—Details
    • 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

  • Embodiments of the present application relate to the field of computing devices, and in particular, to a computing node and a computing device.
  • the embodiment of the present application is to improve the power supply density to the mainboard in the computing node.
  • the first aspect of the embodiment of this application provides a computing node.
  • the computing node includes a mainboard and a flow guide structure.
  • Electronic devices are installed on the first surface of the mainboard; a flow hole is opened along the thickness direction of the mainboard, and the hole wall of the flow hole has a conductive medium; the flow hole is electrically connected to the electronic device;
  • the diversion structure is connected to the power supply and is used to transmit the power supply current output from the power supply; the diversion structure is arranged on one side of the main board and is electrically connected to the hole wall of the through hole, thereby transmitting the power supply current to the through hole along the thickness direction of the main board. inside the flow hole.
  • Electronic devices there are one or more electronic devices on the motherboard, which may include one or more processors. Electronic devices may also include memory.
  • the flow guide structure and the hole wall of the through hole can be fixedly connected through a conductive fixing piece.
  • the power supply current is first conducted outside the motherboard through the conductive structure, and enters the motherboard through the electrical connection between the conductive structure and the through hole of the motherboard.
  • the power supply current is transmitted along the through-hole in the thickness direction of the motherboard, thereby reaching the power supply end of the electronic device to realize power supply for the electronic device.
  • the airflow guide structure and the mainboard are independent structures, the airflow guide structure with appropriate flow capacity can be selected and set according to the power required by the mainboard to be powered, without being limited by the flow capacity of the mainboard. This improves the power supply density of computing nodes.
  • the mainboard includes a current-carrying layer extending along the transverse direction of the mainboard; the current-carrying layer is electrically connected to the hole wall of the through-flow hole; the through-flow hole is electrically connected to the electronic device, including : The through hole is electrically connected to at least one electronic device through the current carrying layer.
  • the current-carrying layer is in contact with the hole wall of the through-hole to achieve electrical connection.
  • the current-carrying layer and the electronic device can be electrically connected through vias. Therefore, the power supply current is transmitted along the through-hole to the current-carrying layer.
  • the power supply current is transmitted along the transverse direction of the motherboard, and then transmitted along the thickness direction of the motherboard through the via hole to the power supply end of the electronic device.
  • the plurality of through holes include a first through hole, and the first through hole penetrates the main board along the thickness direction of the main board; the hole wall of the first through hole is in contact with the current-carrying layer contacts for electrical connection.
  • the first through-flow hole and the air-guiding structure can be fixedly connected through a conductive fixing piece, thereby ensuring the structural stability of the air-guiding structure and the main board. Moreover, since the conductive fixing member is disposed in the first through-flow hole, the flow rate of current in the first through-flow hole is increased, and the longitudinal flow capacity of the motherboard is improved.
  • the electronic device includes a processor module; there are a plurality of through holes, and the plurality of through holes include a second through hole; the motherboard further includes a high conductivity portion;
  • the two through-flow holes extend along the thickness direction of the main board, and the first orifice of the second through-flow hole is used for guiding and The flow structure is connected; the second orifice of the second through-flow hole is connected to the high-conductivity portion; the high-conductivity portion extends from the second orifice along the thickness direction of the motherboard to the first surface of the motherboard, and contacts the power supply end of the processor module .
  • the first opening and the flow guide structure can be connected via an electrically conductive fastener.
  • the conductive fixing member and the hole wall of the second through-flow hole jointly conduct electricity in the second through-flow hole, thereby ensuring a large longitudinal flow capacity. Furthermore, by arranging a high-conductivity portion connected between the second through-hole and the processor module, the current can be directly and stably transmitted to the surface of the motherboard, so that it can be connected to the processor module without relying on the circuit inside the motherboard. Other layer structures carry current, thereby improving the reliability and stability of power supply to the processor.
  • the cross-sectional area of the high-conductivity portion is greater than or equal to the cross-sectional area of the second through-flow hole.
  • the longitudinal flow capacity of the motherboard can be improved to meet the processor's demand for large current power supply.
  • the cross-sectional area of the high-conductivity portion is gradually widened from the second opening of the second through-flow hole toward the first surface of the main board.
  • the shape of the high-conductivity portion by setting the shape of the high-conductivity portion, the internal resistance of the high-conductivity portion can be reduced, the amount of heat generated can be reduced, and the shape and area of the high-conductivity portion exposed on the first surface of the motherboard can be adjusted to adapt to the switching device. power supply end.
  • the second orifice and the high-conductivity portion of the second through-flow hole are connected at a first position of the current-carrying layer; the first position of the current-carrying layer is also connected to at least one The through holes are electrically connected.
  • the high-conductivity portion is electrically connected to the second through-flow hole and the first through-flow hole at the same time, the current in the second through-flow hole and the first through-flow hole can be simultaneously obtained to power the processor.
  • the second through-flow hole is prevented from concentrating heat due to its large carrying capacity, causing local deformation of the motherboard.
  • the processor can obtain current through the first through-flow hole, thereby ensuring stable power supply.
  • the current-carrying layer includes a plurality of first conductive layers, and the first conductive layers are used to conduct the supply current; the plurality of first conductive layers are arranged along the transverse direction of the motherboard, and A plurality of first conductive layers are arranged at intervals; each first conductive layer is electrically connected to at least one through hole.
  • the first conductive layer can be disposed locally and in blocks, thereby forming multiple first conductive layers, in order to realize power supply to the electronic devices on the motherboard. At the same time, it effectively reduces the amount of copper laid between the motherboard layers, shortens the flow path of the current in the motherboard layers, and reduces the flow area, thereby reducing the heat generated by the motherboard itself and improving the working efficiency of the motherboard. Security and stability.
  • the current-carrying layer includes a first conductive layer, the area of the first conductive layer is smaller than the cross-sectional area of the motherboard; the first conductive layer is electrically connected to the through hole.
  • the power supply current that needs to be transmitted by the current-carrying layer is reduced, so that the area of the copper layer laid on the current-carrying layer can be reduced. .
  • the smaller copper layer area can reduce the heat generated inside the motherboard.
  • the current-carrying layer includes a first layer and a second layer arranged sequentially along the thickness direction of the motherboard; the first layer includes a first conductive layer, and the second layer includes a second conductive layer. layer; the second conductive layer is electrically connected to the through hole; the thickness of the second conductive layer is less than or equal to the thickness of the first conductive layer.
  • the orthographic projection of at least one second conductive layer on the first layer at least partially overlaps with the first conductive layer; and the orthographic projection of the second conductive layer partially overlaps with the first conductive layer.
  • conductive layer may be electrically connected in a direction along the thickness of the motherboard.
  • the longitudinal flow capacity of the motherboard is improved, and the large-scale flow on the first surface is improved. It ensures the stability of the power supply of power devices and also avoids local overheating caused by excessive current carrying capacity of a single conductive layer in the motherboard.
  • the motherboard further includes a signal layer, the signal layer and the current-carrying layer are arranged on the same layer; the signal layer includes one or more third conductive layers, and the third conductive layer is arranged on the first One side of the conductive layer, or between two adjacent first conductive layers.
  • the first conductive layer in the current-carrying layer can be partially laid, so that the signal layer and the current-carrying layer can be placed on the same layer, reducing the thickness of the motherboard.
  • the reduction in motherboard thickness can make it easier to weld electronic devices and reduce board manufacturing costs.
  • the motherboard further includes a ground layer, and the ground layer and the current-carrying layer are arranged on the same layer; the ground layer includes one or more fourth conductive layers, and the fourth conductive layers are arranged on the first One side of the conductive layer, or between two adjacent first conductive layers.
  • the first conductive layer in the current-carrying layer can be partially laid, so that the ground layer and the current-carrying layer can be placed on the same layer, reducing the thickness of the motherboard.
  • the reduction in motherboard thickness can make it easier to weld electronic devices and reduce board manufacturing costs.
  • the mainboard has a second surface facing away from the first surface; the mainboard includes two current-carrying layers, one of which is disposed close to the first surface of the mainboard, and the other current-carrying layer.
  • the layer is arranged close to the second surface of the motherboard; the motherboard also includes at least one functional inner layer, and the functional inner layer is any one or more of a signal layer, a power layer, or a ground layer.
  • the functional inner layer is the signal layer and power layer set in the same layer.
  • bidirectional power supply can be achieved, so that electronic devices can be disposed on both surfaces of the motherboard. And the two current-carrying layers are powered together, further improving the flow capacity of the motherboard.
  • the air guide structure includes one or more air guide bars; the air guide bars extend along any one of the length direction, width direction or diagonal direction of the main board.
  • the guide bar can provide vertical power supply to more high-power electronic devices, thereby improving power supply flexibility.
  • the flow guide structure includes a plurality of stacked flow guide sheets, and an anti-corrosion layer sandwiched between two adjacent layers of flow guide sheets.
  • the anti-corrosion layer is isolated, which can isolate or slow down the downward spread of corrosion, thereby reducing the impact of corrosion on the guide strips.
  • the overall flow capacity of the structure ensures stable power supply to the motherboard.
  • the corresponding number of guide plates can be selected according to the required flow rate, it is helpful to match computing nodes with different flow requirements and achieve universal matching for different computing nodes.
  • the multiple main boards include a first main board and a second main board; the second main board is located on the first One side of the main board, and the first surface of the first main board and the first surface of the second main board face the same direction; the air guide structure includes a first air guide bar and a first connecting bar, and the first air guide bar is arranged on the first main board One side of the first connecting bar is fixedly connected to the through hole of the first main board; one end of the first connecting bar is fixedly connected to the first guide bar, and the other end of the first connecting bar is connected to the through hole of the second main board.
  • the power supply to multiple motherboards is realized through the improvement of the diversion structure, thereby increasing the power supply density. Since multiple motherboards are provided, the computing power of the computing node is increased.
  • the plurality of mainboards include a third mainboard and a fourth mainboard; the third mainboard and the fourth mainboard are arranged adjacent to each other, and the first surface of the third mainboard The first surfaces of the main board and the fourth main board face opposite sides respectively; the air guide structure is sandwiched between the third main board and the fourth main board, and is fixed to the through hole of the third main board and the through hole of the fourth main board respectively. connect.
  • the power supply to multiple motherboards is realized through the improvement of the diversion structure, thereby increasing the power supply density. Since multiple motherboards are provided, the computing power of the computing node is increased.
  • the motherboard includes multiple computing units, each computing unit includes a processor, a memory bar disposed on one side of the processor, and a radiator; the computing units are arranged in an array on the motherboard Arrange or arrange in sequence.
  • the power supply capacity is improved through the air diversion structure and the mainboard structure configuration of the embodiment of the present application, and the number of computing units arranged on the mainboard can be increased, thereby increasing the computing power.
  • the computing node further includes a bus device; the bus device has a plurality of power input parts and a power output part; each power input part is connected to the power supply, and the power output part is connected to the flow guide structure connect.
  • the power supply currents output by multiple power modules are combined through a converging device, thereby improving the output capability of the power supply current and increasing the power supply density.
  • the second aspect of the embodiment of the present application provides a computing device.
  • the computing device includes a housing and the computing node in the first aspect; the computing node is installed in the housing.
  • the housing can take on different styles.
  • the casing when the computing device is a rack type or a tower type, the casing can be in a box structure; when the computing device is a blade server, the casing can be in a base style or a box type. There are no specific limitations here.
  • the computing device further includes an immersed cabinet and a power input port, a liquid outlet, and a liquid inlet provided on the immersed cabinet; the immersed cabinet is filled with cooling liquid, and the computing nodes are immersed in the cabinet. in the coolant; the power supply is set outside the immersed cabinet; the power supply and the diversion structure are connected through a power cord; the power input port is for the power cord to penetrate into the immersed cabinet; the liquid outlet is for gaseous or liquid coolant to flow out, and the cooling after cooling The liquid flows back into the immersed cabinet through the liquid inlet.
  • the immersed liquid-cooled computing device is based on the efficient heat dissipation capability of liquid cooling and the high power supply density power supply architecture of the embodiment of the present application, which breaks through the bottleneck of traditional on-board power supply, thereby allowing settings on the motherboard.
  • Multiple processors and attached sockets, radiators and memories can increase computing power density while ensuring the power supply capability and power supply stability to high-power devices on the motherboard.
  • a plurality of parallel air guide structures are provided in the immersion cabinet, and each air guide structure is used to supply power to one or more motherboards;
  • the computing device further includes a confluence device , the manifold device is strip-shaped and extends along the arrangement direction of the plurality of guide structures; each guide structure is fixedly connected to the manifold device.
  • the flow guide structure may be in a strip shape.
  • the power supply density is further improved.
  • the utilization rate of the space in the immersed cabinet is improved.
  • Figure 1 is a top view of a computing node according to an embodiment of the present application.
  • Figure 2 is a side view of a mainboard computing node according to an embodiment of the present application.
  • FIG. 3 is a schematic diagram of an arrangement of an air guide structure relative to a mainboard according to an embodiment of the present application.
  • FIG. 4 is a schematic diagram of another arrangement of the air guide structure relative to the mainboard according to an embodiment of the present application.
  • FIG. 5 is a schematic diagram of another arrangement of the air guide structure relative to the mainboard according to an embodiment of the present application.
  • FIG. 6 is a schematic diagram of another arrangement of the air guide structure relative to the mainboard according to an embodiment of the present application.
  • Figure 7 is an exploded view of a partial structure of a flow guide structure according to an embodiment of the present application.
  • Figure 8 is a side cross-sectional view of a mainboard according to an embodiment of the present application.
  • Figure 9 is a side cross-sectional view of another mainboard according to an embodiment of the present application.
  • FIG. 10 is a side cross-sectional view of yet another mainboard according to an embodiment of the present application.
  • Figure 11 is a side view of a computing node in an architecture in which two motherboards are stacked in the same direction according to an embodiment of the present application.
  • Figure 12 is a side view of another computing node in an architecture in which two motherboards are stacked in the same direction according to an embodiment of the present application.
  • Figure 13 is a side view of another computing node in an architecture in which two motherboards are stacked in the same direction according to an embodiment of the present application.
  • Figure 14 is a side view of another computing node in an architecture in which motherboards are stacked in the same direction according to an embodiment of the present application.
  • Figure 15 is an architectural side view of two motherboards arranged back to back according to an embodiment of the present application.
  • Figure 16 is a side view of another computing node in an architecture in which two motherboards are arranged back-to-back according to an embodiment of the present application.
  • Figure 17 is a side view of a computing node in an architecture in which multiple motherboards are arranged in the same direction according to an embodiment of the present application.
  • Figure 18 is a schematic diagram of the connection structure between a single-phase immersion liquid cooling computing device and an external cooling device according to an embodiment of the present application.
  • Figure 19 is a schematic diagram of a two-phase immersion liquid cooling computing device according to an embodiment of the present application.
  • conductive fixing member 181. first via hole; 182. first buried hole; 136. first position; 20. Guide structure; 21. Guide strip; 211. First guide strip; 221. First connection strip; 222. Second connection strip; 212. Second guide strip; 213. Third guide strip; 223. The third connecting bar; 224. The fourth connecting bar; 214. The fourth guide bar; 23. Guide plate; 24. Anti-corrosion layer; 30. Power module; 40. Convergence device; 41. Electric energy input part; 50. PCIE card; 60. Fan; 70. Hard drive backplane; 80. Hard drive; 90. Shell; 200. Computing equipment; 210. Immersed cabinet; 2101. Power input port; 2102. Liquid outlet; 2103. Liquid inlet; 220. Cooling device.
  • processors such as CPU (Central Processing Unit, central processing unit), TPU (Tensor Processing Unit, tensor processor) , GPU (Graphics Processing Unit, image processor), DPU (Deep learning Processing Unit, deep learning processor), NPU (Neural network Processing Unit, neural network processor), etc.; the power of processors continues to evolve towards high power.
  • CPU Central Processing Unit, central processing unit
  • TPU Torsor Processing Unit, tensor processor
  • GPU Graphics Processing Unit, image processor
  • DPU Deep learning Processing Unit, deep learning processor
  • NPU Neurological network Processing Unit, neural network processor
  • server power supply technologies are mainly based on two-dimensional horizontal methods; for example, the server PSU (Power supply unit, power supply unit) receives the power supply current through the connector on the motherboard, and a copper layer is provided inside the motherboard PCB as a The power supply plane is used to transmit the power supply current introduced from the connector, and then supply power to each component on the PCB board.
  • the motherboard power supply structure higher When the current flow density is high, it can only be achieved by increasing the copper layer thickness or the number of copper layers in the motherboard PCB.
  • embodiments of the present application propose a computing node that improves the power supply structure of the mainboard in the computing node to improve the flow capacity of the power supply current, thereby satisfying the power supply requirements for high-power devices and high-density electronic device layouts on the mainboard. demand to support the development trend of continuous growth in computing power of computing nodes in the future.
  • FIG. 1 is a top view of a computing node 100 according to an embodiment of the present application.
  • the computing node 100 includes a housing 90 , a motherboard 10 disposed in the housing 90 , a power module 30 , a bus device 40 , a flow guide structure 20 , and the like.
  • the motherboard 10 includes a variety of electronic devices 11.
  • the motherboard 10 includes a processor 115, a memory 114, and so on.
  • the processor 115 is a high-power device.
  • the casing 90 usually also includes a PCIE (Peripheral Component Interconnect Express, high-speed serial computer expansion bus standard) card 50, a fan 60, a hard disk backplane 70, a hard disk 80 and other devices, a light board, etc. part.
  • PCIE Peripheral Component Interconnect Express, high-speed serial computer expansion bus standard
  • the composition of the computing node 100 is different relative to rack servers.
  • the blade server includes a base, on which multiple single-board computers, called single-board computers or single-board computers, can be inserted.
  • single-board computers called single-board computers or single-board computers
  • the computing node 100 in this embodiment may not have the above-mentioned casing 90, or may not have the above-mentioned power module 30, converging device 40, PCIE card 50, fan 60, Hard drive 80 backplane 70, hard drive 80, light board and other components.
  • Figure 2 is a side view of a computing node of the mainboard 10 according to an embodiment of the present application.
  • the dotted line in Figure 2 is used to illustrate the current heating transmission path.
  • the power supply may be the power module 30 provided within the housing 90 of the computing node 100, or may be an external power supply provided outside the housing 90 of the computing node 100.
  • the power supply may include multiple power modules 30 , which are stacked in sequence or arranged horizontally along the same direction.
  • the electric energy output by the plurality of power modules 30 can be combined through the converging device 40 , and the combined electric energy through the converging device 40 is transmitted to the guide structure 20 .
  • the power module 30 has a power output terminal
  • the bus device 40 can have multiple power input parts 41 and a power output part; each power input part 41 is connected to one power module 30 , and the power output part is connected to the flow guide structure 20 connection, thereby realizing the convergence of the output currents of multiple power modules 30 .
  • the specific structure of the converging device 40 is not limited here.
  • the bus device 40 includes a bus bar made of a conductive metal, such as copper or aluminum.
  • the bus device 40 may have a strip-shaped structure, and its extending direction is generally consistent with the arrangement direction of the plurality of power modules 30 .
  • the converging device 40 is provided with one or more bends to match the arrangement positions of the multiple power modules 30 , thereby shortening the connection path to each power module 30 .
  • the bus device 40 may also include an overcurrent protector. When the current on the current guide structure 20 or the bus device 40 exceeds the threshold, the overcurrent protector operates to cut off the electrical connection between the bus device 40 and the current guide structure 20 to protect the current. The electronic devices 11 on the motherboard 10 are protected from overcurrent impacts.
  • the converging device 40 is used to combine multiple power modules 30 to improve the current output capability, which is beneficial to supplying power to the motherboard 10 with high power density/high-density computing power, and is conducive to supplying power to multiple motherboards 10 at the same time.
  • the upper and lower surfaces of the motherboard 10 are the first surface 121 and the second surface 122 respectively; the processor 115 and other electronic components are arranged on the first surface 121; of course, they can also are arranged on the first surface 121 and the second surface 122 at the same time.
  • the flow guide structure 20 is connected between the bus device 40 and the mainboard 10 and is used to transmit the electric energy output by the bus device 40 to the mainboard 10 to thereby power the electronic devices 11 on the mainboard 10 .
  • the guide structures 20 are usually arranged in pairs. One guide structure 20 is connected to the positive electrode of the power output part of the bus device 40 for outputting current; the other guide structure 20 (not shown) is connected to the bus. The negative electrode of the power output part of the device 40 is used for current return.
  • the structure and style of the two air guide structures 20 can be the same. No distinction will be made in the following description of the embodiments.
  • the air guide structure 20 is disposed on one side of the main board 10 and generally along the extending direction of the surface of the main board 10 .
  • “One side” here means that the airflow structure 20 can be located on the side where the first surface 121 of the mainboard 10 is located, or on the side where the second surface 122 of the mainboard 10 is located.
  • diversion structures 20 is located on one side of the second surface 122 of the main board 10 and can be attached to the second surface 122 of the main board 10 , or there can be a gap between the second surface 122 and the second surface 122 of the main board 10 .
  • the power supply current is first conducted outside the mainboard 10 through the conductive structure 20 , and then enters into the mainboard 10 through the electrical connection between the conductive structure 20 and the second surface 122 of the mainboard 10 .
  • the power supply current is first conducted outside the motherboard 10 through the flow guide structure 20 and then enters the motherboard 10 through the electrical connection between the flow guide structure 20 and the second surface 122 of the motherboard 10 in a direction generally perpendicular to the surface of the motherboard 10 .
  • the power supply current can be transmitted upward substantially along the thickness direction of the motherboard 10 to reach the power supply end of the electronic device 11 .
  • the transmission path of the power supply current within the motherboard 10 may include a transmission path along the thickness direction of the motherboard 10 to achieve power supply to the electronic device 11 to be powered.
  • the transmission path of the power supply current within the mainboard 10 may also include a transmission path along the transverse direction of the mainboard 10 . For example, after the power supply current enters the motherboard 10 along the thickness direction of the motherboard 10 , it is laterally transmitted along the motherboard 10 to provide power to the electronic device 11 .
  • the air guide structure 20 may include air guide strips 21 and/or air guide plates.
  • FIG. 3 is a schematic diagram of an arrangement of the air guide structure 20 relative to the mainboard 10 according to an embodiment of the present application.
  • the air guide structure 20 includes a air guide bar 21.
  • the air guide bar 21 can extend along the length, width or diagonal direction of the main board 10; of course, it can also extend along other directions. direction extension.
  • FIGS. 4 and 5 are schematic diagrams of another arrangement of the air guide structure 20 relative to the mainboard 10 according to an embodiment of the present application.
  • the air guide bars 21 there are multiple air guide bars 21 , and the multiple air guide bars 21 can be arranged in parallel, and all extend along the length, width, or diagonal direction of the main board 10 .
  • the plurality of air guide bars 21 may also extend in different directions.
  • at least one air guide bar 21 extends along the length direction of the main board 10
  • at least one air guide bar 21 extends along the width direction of the main board 10 .
  • the flow capacities of the multiple guide bars 21 can be different; the cross-sectional area of the guide bars 21 can be adjusted so that each guide bar 21 has a different flow capacity, corresponding to different power levels on the mainboard 10 Electronics 11 are powered.
  • FIG. 6 is a schematic diagram of yet another arrangement of the air guide structure 20 relative to the mainboard 10 according to an embodiment of the present application.
  • the air guide strip 21 can have a linear structure, or can have one or more bending portions according to the arrangement position of the electronic device 11 on the motherboard 10 , thereby adjusting the relative position of the air guide strip 21 to The extended track of the motherboard 10 enables the air guide bar 21 to provide vertical power supply to more high-power electronic devices.
  • the number and extension direction of the air guide bars 21 can be flexibly set according to the arrangement position of the processor 115 and other high-power devices on the motherboard 10 , so that the air guide bars 21 can be used for the processor 115 and other high-power devices.
  • the device supplies power and shortens the lateral flow path of the power supply current in the motherboard 10 , thereby reducing the current density in the motherboard 10 and reducing the heat generated by the motherboard 10 .
  • the air guide structure 20 is plate-shaped and is generally parallel to the main board 10 .
  • the area of the air guide structure 20 may be smaller than the main board 10 , or may be substantially equal to the area of the main board 10 .
  • the flow guide structure 20 arranged in a plate shape can greatly improve the flow capacity, and is connected to the main board 10 at multiple points to realize vertical power supply to more electronic devices 11, thus further reducing the power supply current on the main board.
  • the lateral circulation path within the motherboard 10 greatly reduces the heat generated by the motherboard 10 .
  • the current guiding structure 20 is plate-shaped, the current guiding structure 20 can be vertically connected to a larger number of high-power devices on the motherboard 10 to directly transmit current to these high-power devices, effectively reducing the supply current.
  • the lateral circulation path within the motherboard 10 reduces the current density within the motherboard 10 and reduces the heat generated by the motherboard 10 .
  • the power supply current output from the bus device 40 is conducted to the mainboard 10 through the conductive structure 20 .
  • the air guide structure 20 and the mainboard 10 are independent structures, the air guide structure 20 with appropriate flow capacity can be selected according to the power of the mainboard 10 to be powered without being limited by the flow capacity of the mainboard 10, thereby improving the The power supply density of the computing node 100 is conducive to promoting the development of the computing node 100 in the direction of high-density computing power and high-density power.
  • processors 115 there may be one or more processors 115 on each motherboard 10 .
  • processors 115 there is generally a memory 114 slot and a heat sink 113 packaged together with the processor 115.
  • the motherboard 10 may also include a chipset, PCIE slots, various ports, etc.
  • the type of processor 115 on the motherboard 10 is not limited here, and the multiple processors 115 may be of the same or different types.
  • a processor 115, the processor 115 memory 114 socket and the heat sink 113 can form a computing unit; therefore the motherboard 10 There can be one or more computing units on it. Multiple computing units can be arranged in an array, in a single row at intervals, or in an irregular arrangement, etc.
  • the processor 115 corresponding to each computing unit can be powered vertically through the air guide structure 20 in this embodiment, thereby improving the stability of the power supply.
  • the internal heat of the computing node 100 is relatively large; and because the air guide structure 20 may supply power to multiple motherboards 10 at the same time, the throughput is large, resulting in heat generation. It is also correspondingly larger. If space permits, a gap may be provided between the air guide structure 20 and the powered mainboard 10 .
  • the air-cooled computing node includes a fan 60 , which blows air to take away the heat in the computing node 100 . Therefore, by providing a gap between the air guide structure 20 and the powered mainboard 10, air can be circulated, thereby better dissipating heat from the air guide structure 20 and the mainboard 10.
  • the gap is provided to allow the liquid-cooled working fluid to circulate, thereby taking away the heat on the air guide structure 20 and the mainboard 10 .
  • a heat insulation layer can be provided between the air-guiding structure 20 and the powered mainboard 10 to reduce the flow of air from the air-guiding structure 20 to the powered mainboard 10 .
  • the motherboard 10 conducts heat.
  • the air guide structure 20 is installed independently of the motherboard 10. When directly exposed to the environment, for the air-cooled computing node 100, the air guide structure 20 will be affected by moisture and oxygen in the air. and other corrosive media, thereby affecting the flow capacity.
  • the air guide structure 20 may be provided to include a plurality of laminated air guide sheets 23 .
  • the plurality of guide plates 23 can be fixedly connected and electrically connected by welding at the ends, or metal conductive pillars can be simultaneously penetrated through these guide plates 23 to achieve fixed connection and electrical connection.
  • Each guide plate 23 can be isolated by an anti-corrosion layer 24 .
  • the anti-corrosion layer 24 can be a separate layer sandwiched between two adjacent guide plates 23 , or it can be a coating coated on the surface of each guide plate 23 .
  • the anti-corrosion layer 24 can be made of polymer materials such as acrylic, polyurethane, and epoxy systems; it can also be made of a film structure formed of metal tin or zinc.
  • FIG. 8 is a side cross-sectional view of a motherboard according to an embodiment of the present application.
  • the dotted line in Figure 8 shows the direction of current transmission.
  • the motherboard 10 includes a through hole 15 extending along the thickness direction of the motherboard 10 and a current-carrying layer 13 , a signal layer 133 , a functional inner layer 14 , a ground layer 134 , and the like provided along the transverse direction of the motherboard 10 .
  • the through hole 15 can cooperate with the conductive fixing member 17 to realize the connection between the current guiding structure 20 and the main board 10; the current carrying layer 13 is used to provide a flow path for the power supply current to conduct along the transverse direction of the main board 10.
  • the layer 13 is electrically connected to the hole wall of the through hole 15 , so that the supply current can be obtained from the through hole 15 , and the electronic device 11 arranged along the extension path of the current carrying layer 13 can receive the current from the through hole 181 through the first via hole 181 .
  • the supply current is obtained in layer 13.
  • the through hole 15 is used to realize the connection between the air guide structure 20 and the main board 10 .
  • the hole wall of the through hole 15 is coated with a conductive medium, where the conductive medium may be copper or aluminum.
  • the extending direction of the through hole 15 is generally along the thickness direction of the main board 10 .
  • the flow guide structure 20 is fixedly connected to the through-flow hole 15 through a conductive fixing piece, and is electrically connected while being fixedly connected.
  • the electrically conductive fasteners here can be screws or surface-mounted nuts.
  • Through holes are correspondingly provided on the flow guide structure 20 , and conductive fixing members are sequentially inserted into the through holes 15 and the flow guide structure 20 , thereby achieving fixed connection and electrical connection between the two.
  • FIG. 9 is a side cross-sectional view of another mainboard according to an embodiment of the present application.
  • the dotted line with an arrow indicates the direction of current transmission.
  • Multiple through holes 15 may be provided to achieve multi-point vertical power supply between the air guide structure 20 and the main board 10 .
  • the types of through holes 15 may not be exactly the same.
  • the plurality of through holes 15 include a first through hole 151 , and the first through hole 151 penetrates the main board 10 along the thickness direction of the main board 10 ; the hole wall of the first through hole 151 is in contact with the carrier.
  • the flow layer 13 is in contact for electrical connection.
  • the through-flow hole 15 may also be a blind hole.
  • the closed end of the through hole 15 is electrically connected to the current carrying layer 13 in the motherboard 10 ; the open end of the through hole 15 is for the conductive fixing member 17 to penetrate to connect the flow guide structure 20 .
  • the through hole 15 may be disposed close to the high-power device on the motherboard 10 .
  • the through hole 15 may be located directly below the processor 115 or corresponding to one side of the processor 115 .
  • the power supply current is first transmitted outside the motherboard 10 through the flow guide structure 20, and after reaching the vicinity of the processor 115 to be powered, it enters the through hole 15 through the conductive fixing member 17, and then along the extension direction of the through hole 15, It is directly or indirectly transmitted to the power supply terminal of the processor 115 to realize the vertical power supply of the processor 115 .
  • the through hole 15 is a blind hole
  • the power supply current can also flow out from the through hole 15 and then be transmitted to the power supply terminal of the processor 115 through the current carrying layer 13 inside the motherboard 10 .
  • the processor 115 is usually controlled by a switching device to control the on and off of the power supply, so the through hole 15 can be directly or indirectly electrically connected to the switching device to operate under the control of the switching device. Power is supplied to the processor 115.
  • the processor 115 and the switching device are combined and referred to as the processor module 111.
  • the embodiment of the present application improves the current flow capacity by arranging the flow guide structure 20 . Furthermore, this embodiment further improves the longitudinal flow capacity of the motherboard 10 based on the improvement of the internal structure of the motherboard 10 , so that the large current transmitted on the flow guide structure 20 can be stably and reliably transmitted to the processor 115 on the motherboard 10 . , powering the processor 115.
  • the longitudinal current carrying capacity of the main board 10 is improved by improving the through holes 15 .
  • one or more through holes 15 are opened on the motherboard 10 , and the one or more through holes 15 include at least one second through hole 152 .
  • the first opening of the second through-flow hole 152 is for the conductive fixing member 17 to be inserted to achieve fixed connection and electrical connection with the flow guide structure 20 .
  • the electrically conductive fastener 17 can be a surface mount nut.
  • the second opening of the second through hole 152 is connected to the high conductivity portion 16 .
  • the high-conductivity portion 16 is a solid conductive structure and extends to the top surface of the motherboard 10 along the thickness direction of the motherboard 10 . It achieves electrical connection by directly contacting the power end of the switching device in the processor module 111 , thereby achieving electrical connection to the processor 115 . Powered vertically.
  • the high-conductivity portion 16 is made of conductive material, such as copper or aluminum; and the cross-sectional area of the high-conductivity portion 16 is greater than or equal to the cross-sectional area of the second flow hole 152 , thereby improving the flow capacity and satisfying the processor 115 The need for high current power supply.
  • the high-conductivity portion 16 can also be arranged to gradually widen in the direction of the first surface 121 of the motherboard 10 to gradually increase the cross-sectional area, so as to reduce the internal resistance of the high-conductivity portion 16, reduce the heat generation, and adjust the high-conductivity portion.
  • the shape and area of 16 exposed on the first surface 121 of the motherboard 10 is to adapt to the power supply end of the switching device.
  • the conductive fixing member 17 and the hole wall of the second through-flow hole 152 conduct electricity together in the second through-flow hole 152, thereby ensuring a large longitudinal flow capacity. Furthermore, by arranging the high-conductivity portion 16 to be connected between the second through hole 152 and the processor module 111, current can be directly and stably transmitted to the surface of the motherboard 10, thereby being connected to the processor module 111 without the need for It then relies on other layer structures in the motherboard 10 to carry current, thereby improving the reliability and stability of power supply to the processor 115 .
  • the second orifice of the second through-flow hole 152 and the high-conductivity portion 16 can be connected at the first position 136 of the current-carrying layer 13 , and when the first position 136 is also connected to other through-flow holes 15 , for example, when the first through hole 151 is directly or indirectly electrically connected, since the high conductivity portion 16 is electrically connected to the second through hole 152 and the first through hole 151 at the same time, the second through hole 152 and the first through hole 151 can be obtained at the same time.
  • the current in one through hole 151 supplies power to the processor 115, thereby reducing the current carrying pressure on the second through hole 152 and ensuring stable power supply to the processor 115.
  • the processor 115 can obtain current through the first through hole 151 to ensure stable power supply.
  • the interior of the motherboard 10 includes a current-carrying layer 13, a signal layer 133, a functional inner layer 14 and a ground layer 134; each layer can be connected by an insulating layer. isolation.
  • the current-carrying layer 13 is in contact with the wall of the through-hole 15 to achieve electrical connection, so the current transmitted from the conductive structure 20 can be transmitted to the current-carrying layer 13 through the conductive fixture 17 and the wall of the through-hole 15 . Since the current carrying layer 13 extends along the transverse direction of the main board 10 , current can be transmitted along the transverse direction of the main board 10 .
  • the current-carrying layer 13 and the power supply end of the electronic device 11 on the motherboard 10 can be electrically connected by arranging via holes, blind holes or buried holes, thereby realizing connection with the electronic devices. Connection of the power supply terminal of device 11. In practical applications, the current-carrying layer 13 can be used to supply power to medium- and low-power electronic devices 11 .
  • the current carrying layer 13 includes a first conductive layer 1311, and the first conductive layer 1311 can be made of metal copper or aluminum.
  • copper is used as an example.
  • the first conductive layer 1311 is a thick copper layer; specifically, it can be a copper layer of 2 ounces to 4 ounces, for example, a copper layer with a thickness of 2 ounces.
  • the current carrying layer 13 includes a first conductive layer 1311 , and the area of the first conductive layer 1311 is smaller than the cross-sectional area of the motherboard 10 . Since high-power electronic devices can be vertically powered by the second through hole 152 in conjunction with the high-conductivity portion 16 , the power supply current that needs to be transmitted by the current-carrying layer 13 is reduced, so that the area of the copper layer laid on the current-carrying layer 13 can be reduced.
  • the shape of the current-carrying layer 13 may be square or irregular, and its outline may be designed in a linear or curved shape according to the circuit board layout.
  • the current in the conductive structure 20 can be vertically directed to the current-carrying layer 13 conveniently through the through-hole 15, there is no need to lay the first conductive layer 1311 in the entire current-carrying layer 13. Partial laying is possible.
  • the current carrying layer 13 includes a plurality of first conductive layers 1311, and the plurality of first conductive layers 1311 may be electrically connected through local locations, or may be electrically isolated.
  • the first conductive layer 1311 can be disposed locally and in blocks, thereby forming multiple first conductive layers 1311.
  • the current carrying layer 13 may be provided with only one layer.
  • the current-carrying layer includes a first layer 131 , a second layer 132 sequentially arranged along the thickness direction of the motherboard 10 , and an insulating layer 135 sandwiched between the first layer 131 and the second layer 132 .
  • the first layer 131 and the second layer 132 both extend along the transverse direction of the motherboard 10 and are electrically connected to the hole wall of the through hole 15 to obtain current transmitted from the conductive structure 20 .
  • the first conductive layer 1311 and the second conductive layer 1321 may obtain current from different through holes 15 .
  • a copper layer with a thickness within a certain range may be called the first conductive layer 1311, so the thicknesses of the plurality of first conductive layers 1311 may not be equal.
  • a copper layer with a thickness in another range is called the second conductive layer 1321, and the thicknesses of the plurality of second conductive layers 1321 may be unequal.
  • the thickness range of the first conductive layer 1311 and the thickness range of the second conductive layer 1321 may overlap.
  • the current carrying capabilities of the first conductive layer 1311 and the second conductive layer 1321 are different, and the power supply requirements of various electronic devices 11 on the motherboard 10 are also different. Therefore, according to the power supply requirements of different electronic devices 11, it can be connected to the first conductive layer 1311 on the first layer 131 or to the second conductive layer 1321 on the second layer 132 through via holes or blind holes, thereby obtaining an adapted Supply current.
  • the adaptability of the current-carrying capacity of the conductive layer to the power supply requirements of the electronic device 11 on the motherboard 10 can be improved.
  • the insulating layer 135 may be made of corrugated resin material.
  • the insulating layer 135 can block electrical interference between the first layer 131 and the second layer 132, and can support the first layer 131 or the second layer 132.
  • the current-carrying layer 13 can include three or more layers, and a conductive layer for power supply is provided on each layer, so that the electronic devices 11 on the motherboard 10 can be classified according to the power supply current requirements, thereby realizing the electronic control. Staged power supply for device 11.
  • FIG. 10 is a cross-sectional view of another motherboard 10 according to an embodiment of the present application.
  • the longitudinal current carrying capacity of the mainboard 10 can also be improved by improving the current carrying layer 13 .
  • the orthographic projection of at least one second conductive layer 1321 in the second layer 132 on the first layer 131 may be set to at least partially coincide with the first conductive layer 1311. It is assumed here that the projection of the A region of the second conductive layer 1321 coincides with the B region of the first conductive layer 1311. Therefore, in the process of transmitting the power supply current to the first surface 121 of the motherboard 10, the first buried hole in FIG. 10 can be used.
  • the first buried via 182 electrically connects area A and area B along the thickness direction of the motherboard 10, thereby improving the longitudinal flow capacity of the motherboard 10, improving the stability of the power supply to the high-power devices on the first surface 121, and also avoiding the possibility of a single unit inside the motherboard 10.
  • the conductive layer may cause local overheating due to excessive carrying capacity.
  • the first buried via 182 may be replaced by a through hole, a blind hole, or other solid conductor structure.
  • the signal layer 133 is used to conduct signals between the electronic devices 11 .
  • the current in the conductive structure 20 can be vertically directed to the current-carrying layer 13 conveniently through the through-hole 15, there is no need to lay the first conductive layer 1311 in the entire current-carrying layer 13, but can conduct partial layout. Therefore, in one implementation, the area of the current carrying layer 13 where the first conductive layer 1311 is not laid can be used to set the signal layer 133; for example, the signal layer 133 and the first layer 131 are set on the same layer, thereby reducing the thickness of the motherboard 10 , improve the space utilization within the motherboard 10.
  • the signal layer 133 can be provided on the same layer as one of the first layer 131 or the second layer 132, or can be provided with the first layer 131 and the second layer 132 at the same time.
  • the signal layer 133 is also divided into two layers at this time.
  • a third conductive layer 1331 for conducting signals is provided in the current carrying layer 13 .
  • the third conductive layer 1331 can also be made of metal copper or aluminum.
  • the thickness of the third conductive layer 1331 can be smaller than the thickness of the first conductive layer 1311 . Specifically, it can be 0.5 ounces to 2 ounces of copper, for example, a copper layer with a thickness of 1 ounce.
  • the third conductive layer 1331 and the electronic device 11 on the motherboard 10 can be electrically connected by providing via holes, blind holes or buried holes, thereby transmitting signals between the electronic devices 11 .
  • the first conductive layer 1311 on the first layer 131 may include one or more first conductive layers 1311.
  • the third conductive layer 1331 may be disposed on one side of the first conductive layer 1311.
  • the gap areas between conductive layers 1311 may vary, so one or more third conductive layers 1331 may be laid in each gap.
  • the plurality of third conductive layers 1331 may be electrically connected or electrically isolated, which is determined according to the layout design of the motherboard 10 .
  • the signal layer 133 and the second layer 132 are arranged on the same layer similarly. No further details will be given here.
  • the entire copper layer or aluminum layer can be laid in the board layer during the board manufacturing process, and the first conductive layer with different thicknesses can be produced by etching. 1311 and the third conductive layer 1331, thereby improving the board manufacturing efficiency.
  • the first conductive layer 1311 in the current carrying layer 13 can be partially laid, so that the signal layer 133 and the current carrying layer 13 can be placed on the same layer, reducing the thickness of the motherboard 10 .
  • the reduction in the thickness of the motherboard 10 can make it easier to weld the electronic device 11 and reduce the board manufacturing cost.
  • the ground layer 134 is used to return the current returned by the electronic device 11 to the ground.
  • the ground layer 134 and the current carrying layer 13 may be provided independently of each other.
  • the ground layer 134 is provided close to the second surface 122 of the main board 10
  • the current-carrying layer 13 is provided close to the first surface 121 of the main board 10 . Impedance matching between the ground layer 134 and the current-carrying layer 13 can be achieved by setting the distribution and thickness of the copper layer on the ground layer 134 .
  • the ground layer 134 can be arranged using the area on the current carrying layer 13 where no conductive layer is laid, and the ground layer 134 and the current carrying layer 13 are arranged on the same layer.
  • the ground layer 134 includes a fourth conductive layer 1341, and the fourth conductive layer 1341 may also be a copper or aluminum layer.
  • the ground layer 134 may be placed on the same layer as one of the first layer 131 or the second layer 132 , or may be placed on the same layer as both the first layer 131 and the second layer 132 .
  • the first conductive layer 1311 on the first layer 131 may include one or more first conductive layers 1311.
  • the fourth conductive layer 1341 may be disposed on one side of the first conductive layer 1311.
  • the gap area between conductive layers 1311 may vary, so one or more fourth conductive layers 1341 may be laid in each gap.
  • the plurality of fourth conductive layers 1341 may be electrically connected or electrically isolated. Specifically, Determined based on motherboard 10 layout design.
  • ground layer 134 and the second layer 132 are arranged on the same layer similarly. No further details will be given here.
  • the motherboard 10 may also include one or more functional inner layers 14 , where the functional inner layers 14 may be one or more of a signal layer, a power layer, or a ground layer. Whether the functional inner layer 14 is provided and the number of layers can be determined according to the signal transmission amount and power supply requirements of the electronic device 11 on the motherboard 10 . In some other implementations, the provision of functional inner layer 14 is not necessary.
  • the number of the current carrying layers 13 may be one or more.
  • two current-carrying layers 13 may be provided, namely a first current-carrying layer and a second current-carrying layer.
  • the first current-carrying layer may be provided close to the first surface 121 of the motherboard 10
  • the second current-carrying layer It can be disposed close to the second surface 122 of the motherboard 10 .
  • One or more functional inner layers 14 may be provided between the first current-carrying layer and the second current-carrying layer.
  • the first current-carrying layer and/or the second current-carrying layer may be connected to the signal layer 133,
  • the ground layer 134 is provided on the same layer.
  • the second current-carrying layer may also be replaced by the ground layer 134 .
  • the first current-carrying layer may only be provided on the same layer as the signal layer 133 .
  • the computing node 100 may have only one mainboard 10 or multiple mainboards 10 at the same time.
  • the computing node 100 includes multiple motherboards 10 , and the multiple motherboards 10 are stacked in the same direction.
  • "Plural” here refers to two or more than two.
  • the stacking direction can be upward stacking or horizontal stacking.
  • “Same direction” means that the electronic devices 11 on the multiple motherboards 10 are all disposed on the first surface 121 .
  • Figure 11 is a side view of a computing node in an architecture in which two motherboards are stacked in the same direction according to an embodiment of the present application.
  • the plurality of motherboards 10 include a first motherboard 10a and a second motherboard 10b.
  • the second motherboard 10b is located on one side of the first motherboard 10a; here, the upper side is taken as an example. Since the electronic device 11 is arranged on the first main board 10a, the height of the gap between the first main board 10a and the second main board 10b is relatively large.
  • the structure of the air guide structure 20 can be set according to the relative positional relationship of the multiple motherboards 10, thereby providing power to multiple motherboards 10 at the same time and improving power supply density.
  • the air guide structure 20 includes a first air guide strip 211 and a first connecting strip 221 .
  • the first flow guide bar 211 may be disposed on the upper side of the first main board 10a, and the current on the first flow guide bar 211 is transmitted downward to the first main board 10a.
  • One end of the first connecting bar 221 is fixedly connected to the first guide bar 211, and the other end is fixedly connected to the second mainboard 10b to deliver current to the second mainboard 10b and support the second mainboard 10b.
  • the first connecting strip 221 can conduct current, and on the other hand, it can be used to support the second motherboard 10b, thereby improving the structural stability within the computing node 100.
  • the first air guide strip 211 and the electronic device 11 on the motherboard 10 are both located on the same side of the motherboard 10 . Since the processor 115, memory 114 and other components on the motherboard 10 are relatively high, in order to avoid these relatively high electronic components 11, the first air guide bar 211 can be arranged using any one or more of the following three solutions. :
  • the first guide strip 211 can be bent to change its trajectory to avoid these taller electronic devices 11 .
  • first guide bars 211 may be provided. Each segment is individually connected to the power module 30 or the bus device 40 .
  • a computing unit 112 is formed by a processor 115 , a memory 114 , and a heat sink 113 .
  • Two first air guide bars 211 are respectively arranged on both sides of the computing unit 112 , and the two first air guide bars 211 may be connected to the same or different power modules 30 or bus devices 40 respectively.
  • Each guide bar 21 is fixedly connected to the mainboard 10 respectively, and the adjacent guide bars 21 can be electrically connected through the current-carrying layer 13 in the mainboard 10 to ensure continuous transmission of power supply current.
  • the height of the first air guide bar 211 is higher than the electronic devices on the motherboard 10 that need to be avoided.
  • a second connecting bar 222 is provided to connect between the first air guide bar 211 and the main board 10 .
  • the first connection bar 221 may not be provided, and the first air guide bar 211 is directly connected to the second mainboard 10b.
  • the first air guide bar 211 can also be disposed on the lower side of the first motherboard 10a.
  • the first connecting bar 221 can be connected to the second motherboard by penetrating the first motherboard 10a. 10b fixed connection.
  • the first connection bar 221 may also be connected to the second motherboard 10b in an indirect manner.
  • the second air guide bar 212 is connected to the second main board 10 b by providing a second air guide bar 212 , wherein the second air guide bar 212 extends substantially along the surface of the second main board 10 b.
  • first air guide bars 211, second air guide bars 212, and first connecting bars 221 can be one or more.
  • first connecting strip 221 to penetrate the second mainboard 10b or adding connecting strips, more layers of mainboards 10 can be stacked on the second mainboard 10b, thereby meeting the power supply demand and achieving an increase in computing power density.
  • the second mainboard 10b can also be other types of circuit boards in the computing node 100, such as a riser board.
  • the computing node 100 includes multiple mainboards 10 , and two mainboards 10 among the multiple mainboards 10 are arranged in a "back-to-back" structure. Each motherboard includes multiple computing units 112 . The computing node 100 may include one or more "back-to-back" motherboard 10 arrangements.
  • the two mainboards 10 in a "back-to-back" structure include a third mainboard 10c and a fourth mainboard 10d.
  • the third main board 10c and the fourth main board 10d may have different areas and may also have different shapes.
  • the first surface 121 of the third main board 10c and the first surface 121 of the fourth main board 10d face two different directions respectively.
  • FIG. 15 is a side view of the architecture of two motherboards arranged back to back according to an embodiment of the present application.
  • the air guide structure 20 is sandwiched between the third main board 10c and the fourth main board 10d, and the air guide structure 20 is fixedly connected to the third main board 10c and the fourth main board 10d respectively.
  • the current guiding structure 20 supplies power to the third main board 10c by conducting current upward, and supplies power to the fourth main board 10d by conducting current downward.
  • the air guide structure 20 may only include the third air guide bar 213.
  • Figure 16 is a side view of another computing node in an architecture in which two motherboards are arranged back-to-back according to an embodiment of the present application.
  • the air guide structure 20 may also include third connecting bars 223 and fourth connecting bars 224 .
  • the third connecting bar 223 is fixedly connected between the third conductive bar 213 and the third main board 10c, and is used to transmit the current on the third conductive bar 213 to the third main board 10c.
  • the fourth connection bar 224 is fixedly connected between the third conductor bar 213 and the fourth main board 10d, and is used to transmit the current on the third conductor bar 213 to the fourth main board 10d.
  • the number of the third flow guide bar 213, the third connecting bar 223 and the fourth connecting bar 223 may be one or more.
  • connection bar 223 nor the fourth connection bar 224 is necessary, and can be reasonably set according to the spacing between the third main board 10c and the fourth main board 10d.
  • the power supply density is doubled and the PUE (Power Usage Effectiveness) is reduced.
  • FIG. 17 is a side view of the computing node 100 in an architecture in which multiple motherboards are arranged in the same direction according to an embodiment of the present application.
  • the computing node 100 includes multiple motherboards 10 .
  • the multiple motherboards 10 are arranged side by side along the same direction, and the first surfaces 121 of the multiple motherboards 10 all face the same direction, and there is no gap between two adjacent motherboards 10 .
  • the plurality of main boards 10 are arranged in sequence along the horizontal direction, and the first surfaces 121 of the main boards 10 are all facing upward.
  • the air guide structure 20 can be disposed below multiple mainboards 10 and extend along the arrangement direction of the multiple mainboards 10, thereby achieving simultaneous power supply to multiple mainboards 10.
  • the air guide structure 20 may include a fourth air guide bar 214.
  • the fourth air guide bar 214 extends generally along the arrangement direction of the plurality of motherboards 10, and may be directly or indirectly connected to each motherboard 10 through a connecting bar. Pass current upwards to power each motherboard 10.
  • first embodiment, second embodiment, third embodiment, and fourth embodiment describe some possible arrangements of multiple motherboards 10 and corresponding arrangements of the air guide structures 20 .
  • one computing node 100 will include multiple motherboards 10. Limited by the space conditions within the computing node 100, the arrangement of the multiple motherboards 10 may be diverse. Since the flow capacity and extension shape of the flow guide structure 20 can be customized, it can be realized as two by arranging the flow guide structure 20 The above mainboard 10 supplies power at the same time, thereby increasing the power supply density and meeting the power supply requirements of the high-power devices on the mainboard 10, thus improving the working stability of the computing node 100.
  • Immersion liquid cooling can be a type of direct contact liquid cooling, which immerses the heating electronic device 11 in the cooling liquid to cool down the electronic device 11 .
  • immersion liquid cooling because the heating element is in contact with the coolant, the heat dissipation efficiency is higher than traditional heat dissipation methods, such as air cooling and water cooling; compared with cold plate or spray liquid cooling, its noise is lower lower.
  • FIG. 18 is a schematic diagram of the connection structure between a single-phase immersion liquid-cooled computing device and an external cooling device according to an embodiment of the present application.
  • the computing device 200 includes an immersion cabinet 210 and the computing nodes 100 are disposed in the immersion cabinet 210 .
  • the computing device 200 may also include a cooling device 220 disposed outside the immersion cabinet 210 .
  • the embodiments of the computing node 100 please refer to the above-mentioned first, second, third and fourth embodiments.
  • the computing node 100 includes a motherboard 10 , a flow guide structure 20 , and a confluence device 40 .
  • the motherboard 10 may include multiple computing units 112.
  • the computing unit 112 includes a processor 115, a memory 114, and may also include a heat sink 113 packaged with the processor 115. ;
  • a plurality of computing units 112 are arranged in an array on the motherboard 10 .
  • the arrangement of the motherboard 10 in the immersion cabinet 210 can be in a "back-to-back” arrangement as described in the above embodiment of the computing node 100.
  • the two motherboards 10 form a group of computing nodes 100 in a "back-to-back” arrangement.
  • Each group of computing nodes 100 share a guide structure 20.
  • Multiple groups of computing nodes 100 can be arranged in the immersed cabinet 210, and the multiple groups of computing nodes 100 are arranged approximately in parallel.
  • the bus device 40 may be arranged in a strip shape, extending roughly along the arrangement direction of the plurality of groups of computing nodes 100 .
  • the flow guide structure 20 in each group of computing nodes 100 is fixedly connected to the confluence device 40 .
  • the motherboards 10 in the immersed cabinet 210 may also be arranged in a "same-direction stacking" manner as in the above embodiment, or in a manner in which multiple motherboards 10 are arranged in the same direction.
  • the power supply can be set outside the immersed cabinet 210.
  • the immersed cabinet 210 is provided with a power input port 2101; the power module 30 and the diversion structure 20 are connected through a power cord; the power input port 2101 allows the power cord to penetrate into the immersed cabinet 210. .
  • the power module 30 is connected to the bus device 40 .
  • the power cord and the power input port 2101 need to be sealed to prevent coolant from overflowing.
  • the coolant absorbs the heat of the electronic devices 11 on the motherboard 10 in the immersion cabinet 210, it will flow out through the liquid outlet 2102. After being cooled by the external cooling device 220, it will flow back to the immersion cabinet 210 through the liquid inlet 2103 in the immersion cabinet 210. Inside.
  • the cooling device 220 provided outside the immersed cabinet 210 may include a circulation pump, a heat exchanger and a circulation pipeline.
  • the coolant in the immersion cabinet 210 may be electronic fluoride, but the electronic fluoride remains in a liquid state.
  • the motherboard 10 is directly immersed in the electronic fluoride liquid, and heat is transferred from the electronic devices 11 on the motherboard 10 to the cooling liquid.
  • Cooling device 220 may include a circulation pump and a heat exchanger.
  • the liquid outlet 2103 on the cabinet body of the immersed cabinet 210, the circulation pump, the heat exchanger, and the liquid inlet 2102 form a circulation loop through pipelines.
  • the electronic fluoride liquid with a higher temperature flows out from the liquid outlet 2103, flows in the circulation loop under the power of the circulation pump, and conducts heat exchange with the cooling water in the heat exchanger, thereby forming an electronic fluoride liquid with a lower temperature.
  • the electronic fluorinated liquid with a lower temperature then flows back into the immersion cabinet 210 through the liquid inlet 2102 .
  • the circulating cooling water in this heat exchanger can be provided by a cooling water tower and/or a dry cooler.
  • the immersed liquid-cooled computing device 200 in this embodiment is based on the efficient heat dissipation capability of liquid cooling and the high power supply density power supply architecture of the embodiment of the present application, breaking through the bottleneck of traditional on-board power supply, thereby allowing at least four devices to be installed on the motherboard 10
  • a processor 115 and the attached socket, radiator 113 and memory 114 not only improve the computing power density, but also ensure the power supply capability and power supply stability to the high-power devices on the motherboard 10 .
  • Figure 19 is a schematic diagram of a two-phase immersion liquid cooling computing device according to an embodiment of the present application.
  • the coolant in the immersion cabinet 210 may be electronic fluorinated fluid.
  • cool down The device 220 includes a condensation coil positioned outside the immersion cabinet 210 and a dry cooler.
  • the electronic devices 11 on the motherboard 10 are directly immersed in the electronic fluoride liquid, and heat is transferred from the electrical devices 11 to the electronic fluoride liquid, causing the electronic fluoride liquid to boil and generate steam. Through the boiling and condensation process of electronic fluorinated liquid, the heat transfer efficiency is greatly improved.
  • the steam flows out from the liquid outlet 2102 of the immersed cabinet 210 to the condensation coil, and exchanges heat with the circulating cooling water provided by the dry cooler in the condensation coil. After the steam is condensed and transformed into a liquid state, it still passes through the liquid outlet 2102. Return to the immersion cabinet 210.

Landscapes

  • Engineering & Computer Science (AREA)
  • Microelectronics & Electronic Packaging (AREA)
  • Structure Of Printed Boards (AREA)
  • Cooling Or The Like Of Electrical Apparatus (AREA)

Abstract

本申请实施例提供了一种计算节点及计算设备。计算节点包括主板和导流结构，主板的第一表面上安装有电子器件；沿主板的厚度方向开设有通流孔，通流孔的孔壁具有导电介质；通流孔与电子器件电连接；导流结构供电源连接，用于传输自电源输出的供电电流；导流结构设置于主板的一侧，且与通流孔的孔壁电连接，从而沿主板的厚度方向将供电电流传输至通流孔内。本申请中，由于导流结构与主板是彼此独立的结构，因此无需受到主板通流能力的限制，从而提高了计算节点的供电密度，有利于促进计算节点向高密算力，高密功率方向发展。

Description

计算节点及计算设备
本申请要求于2022年08月30日提交国家知识产权局、申请号为202211049239.9、申请名称为“计算节点及计算设备”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
本申请实施例涉及计算设备领域，特别涉及一种计算节点及计算设备。
背景技术
随着大数据、云计算及AI(Artificial intelligence，人工智能)的兴起，处理器、内存条、硬盘的处理核数、颗粒数量、容量的不断增加，系统功耗也随之大幅增加(单个处理器功耗由200w演进到1000w)，因此对数据中心及服务器的供电能力诉求越来越高；然而，受限于当前传统水平供电架构下，通流密度低，能效差，难以满足服务器功率长期演进发展的需求。
发明内容
本申请实施例在于提高对计算节点中主板的供电密度。
本申请实施例第一方面提出一种计算节点。计算节点包括主板和导流结构，主板的第一表面上安装有电子器件；沿主板的厚度方向开设有通流孔，通流孔的孔壁具有导电介质；通流孔与电子器件电连接；导流结构供电源连接，用于传输自电源输出的供电电流；导流结构设置于主板的一侧，且与通流孔的孔壁电连接，从而沿主板的厚度方向将供电电流传输至通流孔内。
在此，主板上的电子器件有一个或多个，可以包括一个或多个处理器。电子器件还可以包括内存。导流结构与通流孔的孔壁可以通过导电固定件实现固定连接。
在第一方面中，在为主板上电子器件供电的过程中，供电电流先经由导流结构在主板外部传导，通过导流结构与主板通流孔的电连接处而进入主板内，在主板的在主板内，供电电流沿通流孔在主板的厚度方向上传输，从而到达电子器件的供电端，实现为电子器件的供电。本申请实施例中，由于导流结构与主板是彼此独立的结构，因此可以根据待供电主板所需的功率，选择设置合适通流能力的导流结构，而无需受到主板通流能力的限制，从而提高了计算节点的供电密度。并且有利于促进计算节点向高密算力，高密功率方向发展。并且，由于主板内无需水平流通大电流，因此大大降低了主板的发热量，提高了计算节点工作的安全性。
在第一方面的一种可能的实现方式中，主板内包括沿主板横切方向延伸的载流层；载流层与通流孔的孔壁电连接；通流孔与电子器件电连接，包括：通流孔通过载流层与至少一个电子器件电连接。
在这种实现方式中，载流层与通流孔的孔壁通过接触以实现电连接。载流层与电子器件可以通过过孔实现电连接。因此供电电流沿通流孔传输至载流层，在载流层上，供电电流得以沿主板的横切方向传输，进而再通过过孔沿主板厚度方向传输至电子器件的供电端。
在第一方面的一种可能的实现方式中，多个通流孔中包括第一通流孔，第一通流孔沿主板的厚度方向贯穿主板；第一通流孔的孔壁与载流层接触，用于实现电连接。
第一通流孔与导流结构可以通过导电固定件固定连接，从而保证导流结构与主板的结构稳定性。并且由于导电固定件穿设在第一通流孔内，从而提高了电流在第一通流孔内的通流量，提高了主板的纵向通流能力。
在第一方面的一种可能的实现方式中，电子器件中包括处理器模块；通流孔有多个，多个通流孔中包括第二通流孔；主板内还包括高导部；第二通流孔沿主板的厚度方向延伸，第二通流孔的第一孔口供与导 流结构连接；第二通流孔的第二孔口与高导部连接；高导部自第二孔口沿主板的厚度方向延伸至主板的第一表面，并与处理器模块的供电端接触。在此第一孔口与导流结构可以通过导电固定件连接。
第二通流孔内由导电固定件以及第二通流孔的孔壁共同导电，从而保证较大的纵向通流能力。进一步地，通过设置高导部连接在第二通流孔和处理器模块与之间，从而实现直接、稳定地将电流传输至主板表层，从而得以与处理器模块连接，无需再依赖主板内的其他层结构进行载流，从而提高了对处理器供电的可靠性和稳定性。
在第一方面的一种可能的实现方式中，高导部的横截面面积大于或等于第二通流孔的横截面积。
该种可能的实现方式中，可以提高主板的纵向通流能力，满足对处理器对大电流供电的需求。
在第一方面的一种可能的实现方式中，高导部的横截面积自第二通流孔的第二孔口向主板的第一表面方向呈渐阔设置。
该种可能的实现方式中，通过高导部形状的设置，可以以降低高导部内阻，降低发热量，并且调整高导部裸露在主板第一表面上的形状和面积，以适配开关器件的供电端。
在第一方面的一种可能的实现方式中，第二通流孔的第二孔口、高导部在载流层的第一位置处连接；载流层的第一位置处还至少与一个通流孔电连接。
该种可能的实现方式中，由于高导部同时电连接第二通流孔和第一通流孔，因此可以同时获取第二通流孔和第一通流孔中的电流为处理器供电，从而减小对第二通流孔的载流压力，保障对处理器的稳定供电。另外，避免第二通流孔因载流量较大而造成发热量集中，导致主板局部变形。进一步的，还可以在当第二通流孔因与导流结构连接不稳定导致载流不稳定的情况下，处理器可以通过第一通流孔获取电流，从而保证稳定供电。
在第一方面的一种可能的实现方式中，载流层包括多个第一导电层，第一导电层用于传导供电电流；多个第一导电层沿主板的横切方向排布，且多个第一导电层间隔设置；每个第一导电层与至少一个通流孔电连接。
该种可能的实现方式中，由于导流结构与主板可以有多点连接，因此可以局部且分块设置第一导电层，从而形成多个第一导电层，在实现对主板上电子器件供电的同时，有效的减小了主板板层间铺设的铜量，减短了主板板层内的电流的流经路径以及减小了流经面积，从而能够降低主板自身的发热量，提高主板工作的安全性和稳定性。
在第一方面的一种可能的实现方式中，载流层包括一个第一导电层，第一导电层的面积小于主板的横切面积；第一导电层与通流孔电连接。
该种可能的实现方式中，由于大功率电子器件可以由第二通流孔配合高导部垂直供电，因此减少了载流层需要传输的供电电流，使得载流层铺设的铜层面积可以缩小。较小的铜层面积可以降低主板内部的发热量。
在第一方面的一种可能的实现方式中，载流层包括沿主板厚度方向依次排布的第一层和第二层；第一层包括第一导电层，第二层内包括第二导电层；第二导电层与通流孔电连接；第二导电层的厚度小于或等于第一导电层的厚度。
该种可能的实现方式中，可以根据不同电子器件的供电需求，通过过孔或盲孔连接至第一层上的第一导电层或连接至第二层上的第二导电层，从而获取适配的供电电流。通过将载流层分层设置，能够提高导电层载流能力与主板上电子器件供电需求的适配性。
在第一方面的一种可能的实现方式中，至少一个第二导电层在第一层上的正投影，与第一导电层至少部分重合；且正投影部分重合的第二导电层与第一导电层。在此第二导电层与第一导电层可以在沿主板厚度的方向上电连接。
该种可能的实现方式中，通过对载流层的改进，提高了主板的纵向的通流能力，提高对第一表面上大 功率器件的供电的稳定性，并且也避免主板内，单层导电层因载流量过大而造成局部过热的情况。
在第一方面的一种可能的实现方式中，主板内还包括信号层，信号层与载流层同层设置；信号层包括一个或多个第三导电层，第三导电层设置在第一导电层的一侧，或者相邻两个第一导电层之间。
该种可能的实现方式中，通过供电结构的改进，使得载流层中的第一导电层可以进行局部铺设，从而得以将信号层与载流层同层设置，减小主板厚度。主板厚度的减小可以更加便利电子器件的焊接、减少制板成本。
在第一方面的一种可能的实现方式中，主板内还包括接地层，接地层与载流层同层设置；接地层包括一个或多个第四导电层，第四导电层设置在第一导电层的一侧，或者相邻两个第一导电层之间。
该种可能的实现方式中，通过供电结构的改进，使得载流层中的第一导电层可以进行局部铺设，从而得以将接地层与载流层同层设置，减小主板厚度。主板厚度的减小可以更加便利电子器件的焊接、减少制板成本。
在第一方面的一种可能的实现方式中，主板具有背离第一表面的第二表面；主板内包括两个载流层，其中一个载流层靠近主板的第一表面设置，另一个载流层靠近主板的第二表面设置；主板内还包括至少一个功能内层，功能内层为信号层、电源层或者接地层中的任意一种或多种。例如，功能内层为同层设置的信号层以及电源层。
该种可能的实现方式中，通过设置两个载流层，能够实现双向供电，从而可以实现在主板的两个表面上均设置电子器件。并且两个载流层共同供电，进一步提高了主板的通流能力。
在第一方面的一种可能的实现方式中，导流结构包括一个或多个导流条；导流条沿主板的长度方向、宽度方向或对角线方向中任意一个方向延伸。
该种可能的实现方式中，通过调整导流条相对于主板的延伸轨迹，从而可以使导流条能够为更多的大功率电子器件进行垂直供电，提高了供电灵活性。
在第一方面的一种可能的实现方式中，导流结构包括多个层叠设置的导流片，以及夹设在相邻两层导流片之间的防腐蚀层。
该种可能的实现方式中，当导流结构中位于表面的导流片被腐蚀后，由于有防腐蚀层的隔离，从而可以隔绝或减缓腐蚀向下蔓延的速度，从而降低腐蚀对导流条结构整体通流能力的影响，保证对主板的稳定供电。并且，由于可以根据所需要的通流量选择相应数量的导流片，从而有利于匹配不同通流需求量的计算节点，实现针对不同计算节点的通配性。
在第一方面的一种可能的实现方式中，在第一方面的一种可能的实现方式中，主板有多个，多个主板中包括第一主板和第二主板；第二主板位于第一主板的一侧，且第一主板的第一表面和第二主板的第一表面朝向同一方向；导流结构包括第一导流条和第一连接条，第一导流条设置在第一主板的一侧，且与第一主板的通流孔固定连接；第一连接条的一端与第一导流条固定连接，第一连接条的另一端与第二主板的通流孔连接。
该种可能的实现方式中，通过导流结构的改进实现了对多主板的供电，从而提高了供电密度，由于设置了多个主板，因此提高了计算节点的算力。
在第一方面的一种可能的实现方式中，主板有多个，多个主板中包括第三主板和第四主板；第三主板与第四主板相邻设置，且第三主板的第一表面和第四主板的第一表面分别朝向相对的两侧；导流结构夹设在第三主板和第四主板之间，且分别与第三主板的通流孔和第四主板的通流孔固定连接。
该种可能的实现方式中，通过导流结构的改进实现了对多主板的供电，从而提高了供电密度，由于设置了多个主板，因此提高了计算节点的算力。
在第一方面的一种可能的实现方式中，主板上包括多个计算单元，每个计算单元包括处理器、设置与处理器一侧的内存条，以及散热器；计算单元在主板上呈阵列排布或者依次排列。
该种可能的实现方式中，通过本申请实施例导流结构以及主板结构设置，提高了供电能力，得以提高在主板上布置计算单元的数量，从而提高了算力。
在第一方面的一种可能的实现方式中，计算节点还包括汇流装置；汇流装置上具有多个电能输入部以及电能输出部；每个电能输入部与电源连接，电能输出部与导流结构连接。
该种可能的实现方式中，通过汇流装置对多个电源模块输出的供电电流进行汇流，从而提高了供电电流的输出能力，提高了供电密度。
本申请实施例第二方面提出一种计算设备，计算设备包括壳体以及上述第一方面中的计算节点；所述计算节点安装在所述壳体内。
根据计算设备不同的类型，壳体可以呈现为不同的样式。例如当计算设备为机架式或者塔式时，壳体可以呈一个箱体式结构；当计算设备为刀片式服务器是，壳体可以呈基座样式或者是箱体式。此处不做具体限定。
在第二方面的一种可能的实现方式中，计算设备还包括浸没机柜以及开设在浸没机柜上的电能输入口、出液口和进液口；浸没机柜内容置有冷却液，计算节点浸没于冷却液中；电源设置在浸没机柜的外部；电源与导流结构之间通过电源线连接；电能输入口供电源线穿入浸没机柜内；出液口供气态或者液态的冷却液流出，冷却后的冷却液通过进液口回流至浸没机柜内。
该种可能的实现方式中，浸没式液冷计算设备基于液冷高效的散热能力，以及本申请实施例高供电密度的供电架构，突破了传统板内供电的瓶颈，从而可以允许在主板上设置多个处理器以及附属的插座、散热器以及内存，实现算力密度的提高的同时，保证对主板上大功率器件的供电能力以及供电稳定性。
在第二方面的一种可能的实现方式中，浸没机柜内设置了多个平行设置的导流结构，每个导流结构用于为一个或多个主板供电；所述计算设备还包括汇流装置，汇流装置呈条状，且沿多个导流结构的排布方向延伸；每个导流结构固定连接至汇流装置上。
该种可能的实现方式中，导流结构可以呈条状。通过设置每个导流结构为一个或多个主板供电，从而进一步提高了供电密度。通过在浸没机柜内设置了多个平行设置的导流结构，提高了对浸没机柜内空间的利用率。
附图说明
图1是根据本申请实施例示出的一种计算节点的俯视图。
图2是根据本申请实施例示出的一种主板计算节点的侧视图。
图3是根据本申请实施例示出的一种导流结构相对于主板布置方式的示意图。
图4是根据本申请实施例示出的另一种导流结构相对于主板布置方式的示意图。
图5是根据本申请实施例示出的另一种导流结构相对于主板布置方式的示意图。
图6是根据本申请实施例示出的另一种导流结构相对于主板布置方式的示意图。
图7是根据本申请实施例示出的一种导流结构部分结构拆分图。
图8是根据本申请实施例示出的一种主板的侧面剖视图。
图9是根据本申请实施例示出的另一种主板的侧面剖视图。
图10是根据本申请实施例示出的再一种主板的侧面剖视图。
图11是根据本申请实施例示出的两主板同向堆叠的架构下，一种计算节点的侧视图。
图12是根据本申请实施例示出的两主板同向堆叠的架构下，另一种计算节点的侧视图。
图13是根据本申请实施例示出的两主板同向堆叠的架构下，另一种计算节点的侧视图。
图14是根据本申请实施例示出的主板同向堆叠的架构下，另一种计算节点的侧视图。
图15是根据本申请实施例示出的两主板背靠背布置的架构侧视图。
图16是根据本申请实施例示出的两主板背靠背布置的架构下，另一种计算节点的侧视图。
图17是根据本申请实施例示出的多主板沿同一方向布置的架构下，计算节点的侧视图。
图18是根据本申请实施例示出的一种单相浸没式液冷计算设备与外部冷却装置的连接结构示意图。
图19是根据本申请实施例示出的一种两相浸没式液冷计算设备的示意图。
附图标记说明如下：100、计算节点；
10、主板；11、电子器件；111、处理器模块；112、计算单元；113、散热器；114、内存115、处理
器；121、第一表面；122、第二表面；10a、第一主板；10b、第二主板10c、第三主板；10d、第四主板；13、载流层；131、第一层；1311、第一导电层；132、第二层；1321、第二导电层；133、信号层；1331、第三导电层；134、接地层；1341、第四导电层；135、绝缘层；14、功能内层；15、通流孔；151、第一通流孔；152、第二通流孔；16、高导部；17、导电固定件；181、第一过孔；182、第一埋孔；136、第一位置；
20、导流结构；21、导流条；211、第一导流条；221、第一连接条；222、第二连接条；212、第二导
流条；213、第三导流条；223、第三连接条；224、第四连接条；214、第四导流条；23、导流片；24、防腐蚀层；
30、电源模块；
40、汇流装置；41、电能输入部；
50、PCIE卡；60、风扇；70、硬盘背板；80、硬盘；90、壳体；
200、计算设备；210、浸没机柜；2101、电能输入口；2102、出液口；2103、进液口；220、冷却装
置。
具体实施方式
为了使本技术领域的人员更好地理解本申请实施例方案，下面将结合本申请实施例中的附图，对本申请实施例中的技术方案进行清楚的描述。
应当理解的是，本申请实施例提及的“多个”是指两个或两个以上。在本申请实施例的描述中，除非另有说明，“/”表示或的意思，例如，A/B可以表示A或B；本文中的“和/或”仅仅是一种描述关联对象的关联关系，表示可以存在三种关系，例如，A和/或B，可以表示：单独存在A，同时存在A和B，单独存在B这三种情况。另外，为了便于清楚描述本申请实施例的技术方案，采用了“第一”、“第二”等字样对功能和作用基相同的相同项或相似项进行区分。本领域技术人员可以理解“第一”、“第二”等字样并不对数量和执行次序进行限定，并且“第一”、“第二”等字样也并不限定一定不同。
为了进一步说明本发明的原理和结构，现结合附图对本发明的实施例进行详细说明。
随着计算节点算力需求的提高，计算节点主板上需要部署更多数量和更多类型的处理器，例如CPU(Central Processing Unit,中央处理器)、TPU(Tensor Processing Unit,张量处理器)、GPU(Graphics Processing Unit,图像处理器)、DPU(Deep learning Processing Unit,深度学习处理器)、NPU(Neural network Processing Unit,神经网络处理器)等；处理器的功率持续向高功率演进。从物理形态一面，计算节点高密算力的发展，也使得主板上电子器件的排布密度也不断提高，例如半宽式计算节点的出现。由于半宽式计算节点的宽度是常规标准尺寸的计算节点宽度的一半，因此其主板上电子器件的排布非常紧密。计算节点高密算力的发展需要依托于对主板上电子器件稳定可靠的供电。
然而，现有服务器供电技术中，均是以二维水平方式为主；例如，服务器PSU(Power supply unit，电源供应单元)通过主板上的连接器接收供电电流，主板PCB内部通过设置铜层作为供电平面用于传输自连接器导入的供电电流，进而为PCB板上的各元器件供电。然而，基于此类主板供电结构形态，在需要较高 的电流流通密度时，只能通过在主板PCB内增加铜层厚度或铜层的数量来实现，然而过厚或过多数量的铜层会给PCB板打孔布局造成困难，同时也会因持续传导大电流而产生较多热量，导致主板内部温度过高，严重影响各个电子器件的正常工作；甚至，在一些严重的情况下，还可能会引发火灾、爆炸等事故。
对于上述问题，本申请实施例提出一种计算节点，通过对计算节点中主板供电结构的改进，提高对供电电流的通流能力，从而可以满足主板上大功率器件以及高密度电子器件布局的供电需求，支撑计算节点未来算力持续增长的发展趋势。
第一实施例
请参阅图1，图1是根据本申请实施例示出的一种计算节点100的俯视图。在本实施例中，计算节点100包括壳体90、设置在壳体90内的主板10、电源模块30、汇流装置40、导流结构20等。主板10上包括多种电子器件11，例如主板10包括处理器115、内存114等。其中处理器115属于大功率器件。以机架式服务器为例，壳体90内通常还可以包括PCIE(Peripheral Component Interconnect Express，高速串行计算机扩展总线标准)卡50、风扇60、硬盘背板70、硬盘80等器件、灯板等部件。
对于刀片式服务器，计算节点100的组成相对于机架式服务器有所不同。刀片服务器包括基座，基座上可插置多张单板机，单板机或称单板电脑。当将一个单板电脑视为一个计算节点100时，本实施例中的计算节点100可以不具有上述壳体90，也可以不具有上述电源模块30、汇流装置40、PCIE卡50、风扇60、硬盘80背板70、硬盘80、灯板等部件。
请参阅图2，图2是根据本申请实施例示出的主板10计算节点的侧视图。图2中的虚线用于示意电流发热传输路径。电源可以是设置在计算节点100壳体90内的电源模块30，也可以设置在计算节点100壳体90外的外部电源。在一示例中，电源可以包括多个电源模块30，多个电源模块30依次堆叠设置，或者沿同一方向水平排布。多个电源模块30所输出的电能可以通过汇流装置40进行汇流，经过汇流装置40汇流之后的电能传输至导流结构20。
具体地，电源模块30具有电能输出端子，汇流装置40上可以具有多个电能输入部41、以及电能输出部；每个电能输入部41供一个电源模块30连接，电能输出部与导流结构20连接，从而实现对多个电源模块30输出电流的汇流。汇流装置40的具体结构在此不做限定。
在一示例中，汇流装置40包括汇流排，汇流排由导电金属制成，例如铜或铝。汇流装置40具体可以呈条状结构，其延伸方向与多个电源模块30的排布方向大致一致。当多个电源模块30的位置较为分散时，汇流装置40通过设置一个或多个折弯，以匹配多个电源模块30的布置位置，从而减短与各个电源模块30的连接路径。
汇流装置40上还可以包括过流保护器，当导流结构20或汇流装置40上的电流超出阈值时，过流保护器动作，切断汇流装置40与导流结构20之间的电连接，保护主板10上的电子器件11免受过流冲击。
本实施例中利用汇流装置40对多个电源模块30的汇流，提高了电流输出能力，有利于实现对高功率密度/高密算力的主板10供电，以及有利于实现对多主板10同时供电。
在此以图2中所示的方位为参照，主板10的上下两个表面分别为第一表面121和第二表面122；处理器115以及其他电子器件布置在第一表面121上；当然也可以同时布置在第一表面121和第二表面122上。导流结构20连接于汇流装置40与主板10之间，用于将汇流装置40输出的电能传输至主板10内，进而为主板10上的电子器件11供电。
需要说明的是，导流结构20通常成对设置，一个导流结构20连接至汇流装置40的电能输出部的正极，用于输出电流；另一个导流结构20(未图示)连接至汇流装置40的电能输出部的负极，用于电流的回流。两个导流结构20的结构和样式可以相同。在下面对实施例的说明中不做区分。
导流结构20设置在主板10的一侧，且大致沿主板10表面的延伸方向设置。在此“一侧”是指导流结构20可以位于主板10第一表面121所在侧，或者位于主板10第二表面122所在侧。例如，导流结构 20位于主板10的第二表面122的一侧，并且可以贴合于主板10第二表面122，也可以与主板10第二表面122之间存在间隙。在为主板10上电子器件11供电的过程中，供电电流先经由导流结构20在主板10外部传导，通过导流结构20与主板10第二表面122的电连接处进入主板10内。例如，供电电流先经由导流结构20在主板10外部传导，通过导流结构20与主板10第二表面122的电连接处大致以垂直于主板10表面的方向进入主板10内。在主板10内，供电电流可以大致沿主板10的厚度方向向上传输，从而到达电子器件11的供电端。
在此，供电电流在主板10内的传输路径可以包括沿主板10的厚度方向传输的传输路径，实现给待供电电子器件11的供电。供电电流在主板10内的传输路径还可以包括沿主板10横切方向的传输路径。例如，供电电流在沿主板10厚度方向进入主板10内后，通过沿主板10横向传输，实现给电子器件11供电。
本实施例中，导流结构20可以包括导流条21和/或导流板。
请参阅图3，图3是根据本申请实施例示出的一种导流结构20相对于主板10布置方式的示意图。在关于导流条21的一种实现方式中，导流结构20包括一个导流条21，导流条21可以沿主板10的长度、宽度或主板10对角线方向延伸；当然也可以沿其他方向延伸。
请参阅图4和图5，图4和图5是根据本申请实施例示出的另一种导流结构20相对于主板10布置方式的示意图。在关于导流条21的另一种实现方式中，导流条21有多个，多个导流条21可以平行设置，且均沿主板10的长度、宽度或主板10对角线方向延伸。多个导流条21也可以分别沿不同的方向延伸。例如至少一个导流条21沿主板10长度方向延伸，至少一个导流条21沿主板10的宽度方向延伸。其中，多个导流条21的通流能力可以不同；可以通过调整导流条21的截面积，以使每个导流条21具有不同的通流能力，相应为主板10上不同功率等级的电子器件11供电。
请参阅图6，图6是根据本申请实施例示出的再一种导流结构20相对于主板10布置方式的示意图。在这两种实现方式中，导流条21可以呈直线型结构，也可以根据主板10上电子器件11上的布置位置，而具有一个或多个弯折部，从而调整导流条21相对于主板10的延伸轨迹，从而可以使导流条21能够为更多的大功率电子器件进行垂直供电。
本实施例中，可以根据主板10上处理器115以及其他大功率器件的布置位置，灵活设置导流条21的数量和延伸方向的设置，使导流条21能够为处理器115以及其他大功率器件供电，减短供电电流在主板10板内的横向流通路径，从而降低主板10内的电流密度，减少主板10的发热量。
在关于导流板的一实现方式中，导流结构20呈板状，大体平行于主板10。导流结构20的面积可以小于主板10，也可以大致等于主板10的面积。呈板状设置的导流结构20能够较大程度的提高通流能力，且通过与主板10在多点处连接，实现对更多电子器件11的垂直供电，因此进一步减短了供电电流在主板10板内的横向流通路径，大幅降低主板10的发热量。
可以理解的，由于导流结构20呈板状，因此导流结构20可以与主板10上更多数量的大功率器件进行垂直连接，实现直接向这些大功率器件传输电流，有效减短供电电流在主板10板内的横向流通路径，从而降低主板10内的电流密度，减少主板10的发热量。
本实施例方案中通过导流结构20将自汇流装置40输出的供电电流传导至主板10。由于导流结构20与主板10是彼此独立的结构，因此可以根据待供电主板10的功率，选择设置合适通流能力的导流结构20，而无需受到主板10通流能力的限制，从而提高了计算节点100的供电密度，有利于促进计算节点100向高密算力，高密功率方向发展。
每个主板10上可以具有一个或多个处理器115。对应于每个处理器115，一般配置有内存114插槽、以及与处理器115封装在一起的散热器113。主板10上还可以包括芯片组、PCIE插槽以及各种端口等。在此不限定主板10上处理器115的类型，多个处理器115可以是相同或不同的类型。
在此一个处理器115、该处理器115内存114插槽和散热器113可以形成一个计算单元；因此主板10 上可以具有一个或多个计算单元。多个计算单元可以呈阵列方式排布，也可以呈单行间隔排布方式，也可以呈不规则的排布方式等。对应于每个计算单元中的处理器115均可以通过本实施例中的导流结构20进行垂直供电，从而提高供电的稳定性。
由于计算节点100中电子器件11布局紧密、功率密度较大，造成计算节点100内部发热量较大；并且由于导流结构20可能会对多主板10同时供电，因此通流量较大，导致发热量也相应较大。在空间允许的情况下，可以设置导流结构20与被供电主板10之间具有间隙。在风冷型计算节点中，包括风扇60，风扇60通过吹风从而带走计算节点100内的热量。因此通过在导流结构20和被供电主板10之间间隙的设置，可以供空气流通，从而更好的对导流结构20和主板10进行散热。对于液冷型计算节点100，间隙的设置可以供液冷工质流通，从而带走导流结构20和主板10上的热量。
当导流结构20和被供电主板10之间贴合设置或者间隙非常小时，可以在导流结构20和被供电的主板10之间设置隔热层，以减少自导流结构20向被供电的主板10传导的热量。
如前所述，本实施例中导流结构20是独立于主板10设置，直接暴露于环境中时，对于风冷式计算节点100来说，导流结构20会有被空气中的水分、氧气和其他腐蚀性介质腐蚀的风险，从而影响通流能力。
请参阅图7，图7是根据本申请实施例示出的一种导流结构20部分结构拆分图。为了解决这一问题，本实施例中，可以设置导流结构20包括多个层叠设置的导流片23。多个导流片23可以在端部通过焊接实现固定连接及电连接，也可以利用金属导电柱同时贯穿这些导流片23而实现固定连接及电连接。每个导流片23之间可以通过防腐蚀层24进行隔离。
防腐蚀层24可以是一个单独的层，夹设在相邻两个导流片23之间，也可以是涂覆在每个导流片23表面上的涂层。防腐蚀层24的材料具体可以采用丙烯酸、聚氨酯、环氧体系等聚合物材料；也可以采用金属锡、锌形成的膜结构等。当导流结构20中位于表面的导流片23被腐蚀后，由于有防腐蚀层24的隔离，从而可以隔绝或减缓腐蚀向下蔓延的速度，从而降低腐蚀对导流条21结构整体通流能力的影响，保证对主板10的稳定供电。并且，由于可以根据所需要的通流量选择相应数量的导流片23，从而有利于匹配不同通流需求量的计算节点100，实现针对不同计算节点100的通配性。
请参阅图8，图8是根据本申请实施例示出的一种主板的侧面剖视图。图8中虚线为电流传输方向的示意。本实施例中，主板10包括沿其自身厚度方向延伸的通流孔15以及沿主板10横切方向设置的载流层13、信号层133、功能内层14以及接地层134等。通流孔15可以与导电固定件17配合，用于实现导流结构20与主板10之间的连接；载流层13用于为供电电流提供沿主板10横切方向传导的流通路径，载流层13通过与通流孔15的孔壁电连接，从而能够从通流孔15获取供电电流，并且使沿载流层13延伸路径上布置的电子器件11能够通过第一过孔181从载流层13内获取供电电流。
具体地，通流孔15用于实现导流结构20与主板10之间的连接。通流孔15的孔壁涂覆有导电介质，在此导电介质可以是铜或铝。通流孔15的延伸方向大致沿主板10的厚度方向。导流结构20通过导电固定件与通流孔15固定连接，并在固定连接的同时实现了电连接。在此导电固定件可以是螺栓或表贴螺母。在导流结构20上相应设置有通孔，通过导电固定件依次穿设在通流孔15与导流结构20上的通孔内，从而实现两者的固定连接以及电连接。
请参阅图9，图9是根据本申请实施例示出的另一种主板的侧面剖视图。其中，带有箭头的虚线为电流传输方向的示意。通流孔15可以设置多个，以实现导流结构20与主板10之间的多点垂直供电。通流孔15的类型也可以不完全相同。在一种实现方式中，多个通流孔15中包括第一通流孔151，第一通流孔151沿主板10的厚度方向贯穿所主板10；第一通流孔151的孔壁与载流层13接触，用于实现电连接。
在一些其他的实现方式中，通流孔15也可以是盲孔。当通流孔15是盲孔时，通流孔15的封闭端与主板10内的载流层13电连接；通流孔15的开口端供导电固定件17穿入，以连接导流结构20。
通过导流结构20以及通流孔15的设置得以便利地为主板10上的大功率器件供电，而不用考虑大电 流的传输路径的设置限制，以及主板10的载流能力的限制。具体地，通流孔15可以靠近于主板10上的大功率器件设置，例如通流孔15可以位于处理器115的正下方或者对应于处理器115的一侧设置。在供电过程中，供电电流先通过导流结构20在主板10外部传输，到达待供电的处理器115附近后，通过导电固定件17进入通流孔15，进而沿通流孔15的延伸方向，直接或间接地传输至处理器115的供电端，实现为处理器115的垂直供电。例如，当通流孔15是盲孔时，供电电流也可以自通流孔15流出后经过主板10内部的载流层13传输至处理器115的供电端。
在一种实现方式中，在电路设计中，处理器115通常由开关器件控制供电的通断，因此通流孔15可以直接或间接地与该开关器件电连接，以在该开关器件的控制下对处理器115供电，在下述示例中，将处理器115和开关器件合并称为处理器模块111。
基于上述实施例可知，本申请实施例通过设置导流结构20提高了对电流的通流能力。进一步的，本实施例进一步基于主板10内部结构的改进，提高主板10的纵向通流能力，从而能够有效的将导流结构20上传输的大电流稳定可靠的传输至主板10上的处理器115，为处理器115供电。
请继续参阅图9，在一种实现方式中，通过对通流孔15的改进提高主板10的纵向载流能力。具体地，主板10上开设有一个或多个通流孔15，一个或多个通流孔15包括至少一个第二通流孔152。第二通流孔152的第一孔口供导电固定件17插入，以实现与导流结构20的固定连接以及电连接。在此，导电固定件17可以是表贴螺母。第二通流孔152的第二孔口连接有高导部16。高导部16为实心导电结构，且沿主板10厚度方向延伸至主板10顶面，通过与处理器模块111中的开关器件的电源端直接接触的方式实现电连接，进而实现对处理器115的垂直供电。
在此高导部16由导电材料制成，例如铜或铝；且高导部16的横截面面积大于或等于第二通流孔152的横截面积，从而提高通流能力，满足处理器115对大电流供电的需求。
进一步的，还可以设置高导部16向主板10第一表面121的方向呈渐阔设置，实现截面积的逐渐增大，以降低高导部16内阻，降低发热量，并且调整高导部16裸露在主板10第一表面121上的形状和面积，以适配开关器件的供电端。
在本实现方式中，第二通流孔152内由导电固定件17以及第二通流孔152的孔壁共同导电，从而保证较大的纵向通流能力。进一步地，通过设置高导部16连接在第二通流孔152和处理器模块111与之间，从而实现直接、稳定地将电流传输至主板10表层，从而得以与处理器模块111连接，无需再依赖主板10内的其他层结构进行载流，从而提高了对处理器115供电的可靠性和稳定性。
进一步的，可以设置第二通流孔152的第二孔口、高导部16在载流层13的第一位置136处连接，且当该第一位置136处还与其他的通流孔15，例如第一通流孔151，直接或间接电连接时，由于高导部16同时电连接第二通流孔152和第一通流孔151，因此可以同时获取第二通流孔152和第一通流孔151中的电流为处理器115供电，从而减小对第二通流孔152的载流压力，保障对处理器115的稳定供电。另外，避免第二通流孔152因载流量较大而造成发热量集中，导致主板10发生局部变形。进一步的，还可以在当第二通流孔152因与导流结构20连接不稳定导致载流不稳定的情况下，处理器115可以通过第一通流孔151获取电流，从而保证稳定供电。
应当理解，主板10上至少有两个中央处理器115，还可以有其他类型的处理器115。本方案中第二通流孔152与高导部16的配合结构可以设置有多个，以一一对应的方式为各个处理器115供电。
如前所述，本实施例中，沿主板10的横切方向，主板10内部包括有载流层13、信号层133、功能内层14以及接地层134；各个层之间可以通过绝缘层进行隔离。其中，载流层13与通流孔15的孔壁通过接触以实现电连接，因此自导流结构20传输的电流可以经过导电固定件17以及通流孔15的孔壁传输至载流层13。由于载流层13是沿主板10的横切方向延伸，因此可以沿主板10的横切方向传输电流。另外，可以通过设置过孔、盲孔或者埋孔电连接载流层13与主板10上电子器件11的供电端，从而实现与电子 器件11供电端的连接。在实际应用中，可以利用载流层13对中、小功率的电子器件11供电。
为了满足电子器件11的供电需求，载流层13包括第一导电层1311，第一导电层1311可以采用金属铜或铝制成。在本实施例中，均以铜为例，第一导电层1311属于厚铜层；具体可以为2盎司至4盎司的铜层，例如厚度为2盎司的铜层。
请继续参阅图9，在一种实现方式中，载流层13包括一个第一导电层1311，第一导电层1311的面积小于所述主板10的横切面积。由于大功率电子器件可以由第二通流孔152配合高导部16垂直供电，因此减少了载流层13需要传输的供电电流，使得载流层13铺设的铜层面积可以减小。在该实现方式中，载流层13的形状可以是方形、也可以是不规则的形状，其轮廓根据电路板布局可以设计成直线型或者曲线型。
在另一种实现方式中，由于可以便利地通过通流孔15将导流结构20中的电流垂直引至载流层13，因此无需在整个载流层13中铺设第一导电层1311，而可以进行局部铺设。例如，在载流层13内包括多个第一导电层1311，多个第一导电层1311之间可以通过局部部位电连接，也可以电性隔离。本实现方式中，由于导流结构20与主板10可以有多点连接，因此可以局部且分块设置第一导电层1311，从而形成多个第一导电层1311，在实现对主板10上电子器件11供电的同时，有效的减小了主板10板层间铺设的铜量，减短了主板10板层内的电流的流经路径以及减小了流经面积，从而能够降低主板10自身的发热量，提高主板10工作的安全性和稳定性。
在一种实现方式中，载流层13可以有仅设置一层。在另一种实现方式中，载流层包括沿主板10厚度方向依次设置的第一层131、第二层132以及夹设在第一层131和第二层132之间的绝缘层135。第一层131和第二层132均沿主板10的横切方向延伸，且均与通流孔15的孔壁电连接，以获得自导流结构20传输的电流。第一层131上具有至少一个第一导电层1311，第二层132上具有至少一个第二导电层1321；第二导电层1321的厚度小于第一导电层1311的厚度。在此，第一导电层1311和第二导电层1321可以从不同的通流孔15获取电流。
在此，可以将厚度在一定范围内的铜层称为第一导电层1311，因此多个第一导电层1311的厚度可以不相等。将厚度在另一范围内的铜层称为第二导电层1321，多个第二导电层1321的厚度可以不相等。第一导电层1311和厚度范围和第二导电层1321的厚度范围可以有重叠。
由于第一导电层1311和第二导电层1321的载流能力不同，且主板10上各种电子器件11的供电需求也有差异。因此可以根据不同电子器件11的供电需求，通过过孔或盲孔连接至第一层131上的第一导电层1311或连接至第二层132上的第二导电层1321，从而获取适配的供电电流。通过将载流层13分层设置，能够提高导电层载流能力与主板10上电子器件11供电需求的适配性。
绝缘层135可以采用波树脂材料制成。由于绝缘层135可以阻隔第一层131和第二层132之间的电气干扰，并且可以支撑第一层131或第二层132。
应当理解，载流层13可以包括三层以及三层以上，在每层上均设置用于供电的导电层，从而可以根据主板10上电子器件11对供电电流的需求大小进行分类，实现对电子器件11的分级供电。
请参阅图10，图10是根据本申请实施例示出的另一种主板10的剖面图。在此，还可以通过对载流层13的改进，从而提高主板10的纵向载流能力。具体地，可以设置第二层132中的至少一个第二导电层1321在第一层131上的正投影，与第一导电层1311至少部分重合。在此假设第二导电层1321的A区域的投影与第一导电层1311的B区域重合，因而在向主板10第一表面121传输供电电流的过程中，可以利用图10中的第一埋孔182沿主板10的厚度方向电连接A区域和B区域，从而提高主板10的纵向的通流能力，提高对第一表面121上大功率器件的供电的稳定性，并且也避免主板10内，单层导电层因载流量过大而造成局部过热的情况。应当理解，第一埋孔182可以用通孔、盲孔或者其他实心导体结构替换。
信号层133用于传导电子器件11之间的信号。如前所述，由于可以便利地通过通流孔15将导流结构20中的电流垂直引至载流层13，因此无需在整个载流层13中铺设第一导电层1311，而可以进行局部铺设。 因此，在一种实现方式中，可以利用载流层13中未铺设第一导电层1311的区域设置信号层133；例如，将信号层133与第一层131同层设置，从而降低主板10厚度，提高主板10内的空间利用率。
当载流层13包括第一层131和第二层132时，信号层133可以与第一层131或第二层132其中之一同层设置，也可以同时与第一层131和第二层132同层设置，应当理解，此时信号层133也相应分成两层。
在此以信号层133与第一层131同层设置为例。在载流层13内设置用于传导信号的第三导电层1331，第三导电层1331也可以采用金属铜或铝制成，第三导电层1331的厚度可以小于第一导电层1311的厚度。具体可以是0.5盎司至2盎司的铜，例如厚度为1盎司的铜层。可以通过设置过孔、盲孔或者埋孔电连接第三导电层1331与主板10上的电子器件11，从而传输电子器件11间的信号。
在此，第三导电层1331可以有一个或多个。如前所述，第一层131上的第一导电层1311可以包括一个或多个第一导电层1311。当第一层131上仅有一个整体的第一导电层1311时，第三导电层1331可以设置在第一导电层1311的一侧。当第一层131上有多个第一导电层1311时，由于第一导电层1311可以有多个，因此多个第一导电层1311之间的间隙也可以有一个或多个，多个第一导电层1311之间的间隙面积可以不等，因此可以每个上述间隙中铺设一个或多个第三导电层1331。多个第三导电层1331之间可以电连接也可以电性隔离，具体根据主板10版图设计确定。
信号层133与第二层132同层设置与此类似。此处不再赘述。
在将信号层133与载流层13同层设置的实现方式中，可以在制板过程中，在板层内铺设整个铜层或铝层，通过蚀刻的方式制作出厚度不同的第一导电层1311和第三导电层1331，从而提高制板效率。
本实施例通过供电结构的改进，使得载流层13中的第一导电层1311可以进行局部铺设，从而得以将信号层133与载流层13同层设置，减小主板10厚度。主板10厚度的减小可以更加便利电子器件11的焊接、减少制板成本。
接地层134用于将电子器件11返回的电流回流至地。请参阅图9，在一种实现方式中，接地层134可以与载流层13彼此独立设置。例如，设置接地层134靠近主板10第二表面122，载流层13设靠近主板10第一表面121设置。可以通过设置接地层134上铜层的分布以及厚度，以实现接地层134与载流层13的阻抗匹配。
在另一实现方式中，可以利用载流层13上未铺设导电层的区域布置接地层134，将接地层134和载流层13同层设置。具体地，接地层134包括第四导电层1341，第四导电层1341也可以为铜或铝层。接地层134可以与第一层131或第二层132其中之一同层设置，也可以同时与第一层131和第二层132同层设置。
在此，第四导电层1341可以有一个或多个。如前所述，第一层131上的第一导电层1311可以包括一个或多个第一导电层1311。当第一层131上仅有一个整体的第一导电层1311时，第四导电层1341可以设置在第一导电层1311的一侧。当第一层131上有多个第一导电层1311时，由于第一导电层1311可以有多个，因此多个第一导电层1311之间的间隙也可以有一个或多个，多个第一导电层1311之间的间隙面积可以不等，因此可以每个上述间隙中铺设一个或多个第四导电层1341，多个第四导电层1341之间可以电连接也可以电性隔离，具体根据主板10版图设计确定。
接地层134与第二层132同层设置与此类似。此处不再赘述。
如前所述，主板10内还可以包括一个或多个功能内层14，在此功能内层14可以是信号层，也可以是电源层、或接地层中的一种或多种。功能内层14是否设置，以及设置层数可以根据主板10上电子器件11的信号传输量以及供电需求确定。在一些其他的实现方式中，功能内层14的设置不是必须的。
基于上述对主板10各层的说明，可以理解的是，本实施例中，载流层13的数量可以是一个或多个。在一种实现方式中，载流层13可以设置两个，分别为第一载流层和第二载流层，第一载流层可以靠近主板10第一表面121设置，第二载流层可以靠近主板10第二表面122设置。一个或多个功能内层14可以设置在第一载流层和第二载流层之间。在这个排布方式中，第一载流层和/或第二载流层可以与信号层133、 接地层134同层设置。
在另一种实现方式中，也可以将第二载流层替换为接地层134。此时第一载流层可以仅与信号层133同层设置。
第二实施例
计算节点100内可以仅具有一个主板10，也可以同时具有多个主板10。在本实施例中，计算节点100内包括多个主板10，多个主板10同向堆叠设置。“多个”在此指两个或两个以上。堆叠方向可以是向上堆叠，或者是沿水平方向堆叠。“同向”是指多个主板10上的电子器件11均设置在第一表面121上。
请参阅图11，图11是根据本申请实施例示出的两主板同向堆叠的架构下，一种计算节点的侧视图。具体的，多个主板10中包括第一主板10a和第二主板10b，第二主板10b位于第一主板10a的一侧；在此以上侧为例。由于第一主板10a上布置有电子器件11，因此第一主板10a和第二主板10b之间的间隙高度较大。
当多个主板10同向堆叠设置时，可以根据多个主板10的相对位置关系设置导流结构20的结构，从而实现为多个主板10同时提供电能，提高供电密度。
在此，以图11中所示的方位为参照。在一种实现方式中，设置导流结构20包括第一导流条211和第一连接条221。其中，第一导流条211可以设置在第一主板10a的上侧，第一导流条211上的电流向下传输至第一主板10a。第一连接条221的一端与第一导流条211固定连接，另一端固定连接至第二主板10b，以向第二主板10b输送电流并支撑第二主板10b。第一连接条221一方面可以起到传导电流的作用，另一方面可以用于支撑第二主板10b，从而提高计算节点100内的结构稳定性。
在该实现方式中，由于第一导流条211与主板10上的电子器件11均位于主板10的同一侧。而由于主板10上的处理器115、内存114等器件的高度较高，为了避让这些较高的电子器件11，第一导流条211的设置可以采用下述三种方案任意一种或多种：
(1)第一导流条211可以通过折弯，以改变轨迹，从而避让这些较高的电子器件11。
(2)第一导流条211可以设置多个。每段单独与电源模块30或汇流装置40连接。例如，图11中，对于处理器115、内存114、散热器113形成的计算单元112。分别在计算单元112的两侧布置两个第一导流条211，两个第一导流条211可以分别连接至相同或不同的电源模块30或汇流装置40。
(3)第一导流条211可以设置多个。每个导流条21分别与主板10固定连接，相邻导流条21之间可以通过主板10内的载流层13实现电连接，保证供电电流的连续传输。
(4)请参阅图12，通过升高第一导流条211的高度，使第一导流条211的高度高于主板10上需要避让的电子器件。再通过设置第二连接条222连接在第一导流条211与主板10之间。在这种实现方式中，第一连接条221可以不设置，第一导流条211与第二主板10b直接连接。
请参阅图13，在另一种实现方式中，第一导流条211也可以设置在第一主板10a的下侧，此时第一连接条221可以通过贯穿第一主板10a而与第二主板10b固定连接。
请参阅图14，第一连接条221也可以通过间接的方式与第二主板10b连接。例如通过设置第二导流条212与第二主板10b连接，其中第二导流条212大致沿第二主板10b的表面延伸。
应当理解，上述第一导流条211、第二导流条212、第一连接条221的数量均可以设置一个或多个。并且，通过设置第一连接条221贯穿第二主板10b或者增加连接条的方式，得以在第二主板10b之上堆叠更多层的主板10，在满足供电需求的同时，实现算力密度的提高。
在其他的实现方式中，第二主板10b也可以是计算节点100内其他类型的电路板，例如Riser板卡。
在本实施例中，关于电源模块30、汇流装置40、导流结构20以及主板10等部件的结构描述请参照第一实施例，此处不再赘述。
第三实施例
本实施例可以应用于集群或者超算等计算设备中，计算节点100内包括多个主板10，多个主板10中的两两主板10呈“背靠背”结构设置。每个主板上包括多个计算单元112。计算节点100中可以包括一个或多个“背靠背”的主板10排布结构。
具体的，一个“背靠背”结构中的两个主板10包括第三主板10c和第四主板10d。第三主板10c和第四主板10d可以具有不同的面积，也可以具有不同的形状。第三主板10c的第一表面121和第四主板10d的第一表面121分别朝向两个不同的方向。
请参阅图15，图15是根据本申请实施例示出的两主板背靠背布置的架构侧视图。在此以图15中所示方位为例。导流结构20夹设在第三主板10c和第四主板10d之间，且导流结构20分别与第三主板10c和第四主板10d固定连接。导流结构20通过向上传导电流为第三主板10c供电，通过向下传导电流为第四主板10d供电。
在一种实现方式中，当第三主板10c和第四主板10d之间的间距较小时，导流结构20可以仅包括第三导流条213。
请参阅图16，图16是根据本申请实施例示出的两主板背靠背布置的架构下，另一种计算节点的侧视图。在另一种实现方式中，当第三主板10c和第四主板10d之间的间距较大时。导流结构20还可以包括第三连接条223和第四连接条224。第三连接条223固定连接至第三导流条213和第三主板10c之间，用于将第三导流条213上的电流传输至第三主板10c。第四连接条224固定连接在第三导流条213和第四主板10d之间，用于将第三导流条213上的电流传输至四主板10d。第三导流条213、第三连接条223和第四连接条223的数量可以有一个或多个。
应当理解，第三连接条223和第四连接条224均不是必须的，可以根据第三主板10c和第四主板10d的间距合理设置。
本实施例中通过主板10的“背靠背”布置方式，以及导流结构20的设置，实现了供电密度的翻倍，降低了PUE(Power Usage Effectiveness，用电效率)。
在本实施例中，关于电源模块30、汇流装置40、导流结构20以及主板10等部件的结构描述请参照第一实施例，此处不再赘述。
第四实施例
请参阅图17，图17是根据本申请实施例示出的多主板沿同一方向布置的架构下，计算节点100的侧视图。在本实施例中，计算节点100内包括多个主板10，多个主板10沿同一方向并排设置，且多个主板10的第一表面121均朝向同一方向，且相邻两个主板10之间可以具有间隔，也可以接触设置。具体地，多个主板10沿水平方向依次排列，且主板10的第一表面121均朝上。
在此，以图17中的方位为例，导流结构20可以设置在多个主板10的下方，且沿多个主板10的排布方向延伸，从而实现对多个主板10的同时供电。具体地，导流结构20可以包括第四导流条214，第四导流条214大致沿多个主板10的排布方向延伸，且可以直接或者通过连接条间接连接至每个主板10，通过向上传输电流，而为每个主板10供电。
上述第一实施例、第二实施例、第三实施例、第四实施例中记载了关于多个主板10的一些可能的排布方式，以及导流结构20相应的设置方式。应当理解，随着计算节点100算力的不断提高，一个计算节点100内会包括多个主板10，受限于计算节点100内的空间条件，多个主板10的排布方式可以是多样的。而由于导流结构20的通流能力以及延伸形状均可以被定制，因此可以通过设置导流结构20而实现为两个 以上的主板10同时供电，提高供电密度，满足主板10上大功率器件的供电需求，从而提高计算节点100的工作稳定性。
第五实施例
本实施例中提出一种浸没式液冷计算设备200。浸没式液冷可以是一种的直接接触型液冷，它是将发热的电子器件11浸没在冷却液中，实现对电子器件11降温。浸没式液冷中由于发热元件与冷却液接触，散热效率相比于传统的散热方式，例如风冷和水冷，它的散热效率更高些；相对于冷板或喷淋液冷，它的噪音更低。
请参阅图18，图18是根据本申请实施例示出的一种单相浸没式液冷计算设备与外部冷却装置的连接结构示意图。在本实施例中，计算设备200包括浸没机柜210，设置在浸没机柜210内的计算节点100。在一些其他的实施例中，计算设备200还可以包括设置在浸没机柜210外的冷却装置220。计算节点100的实施例请参考上述第一、第二、第三、第四实施例。
如上述计算节点100的实施例中提到，计算节点100包括主板10、导流结构20、汇流装置40。对于高密、集群、超算等类型的计算节点100，主板10上可以包括多个计算单元112，计算单元112包括处理器115、内存114，还可以包括与处理器115封装在一起的散热器113；多个计算单元112在主板10上呈阵列排布。
主板10在浸没机柜210里的布置可以呈如上述计算节点100实施例中所记载的“背靠背”形式设置，两个主板10通过“背靠背”的设置方式形成一组计算节点100，每组计算节点100共用一个导流结构20。浸没机柜210里可以布置多组计算节点100，多组计算节点100大致呈平行设置。汇流装置40可以设置呈条状，大致沿多组计算节点100的排布方向延伸。每组计算节点100内的导流结构20固定连接至汇流装置40上。
在一些其他的实现方式中，主板10在浸没机柜210里的主板10布置的还可以如上述实施例中的“同向堆叠”、以及多主板10沿同一方向排布的方式。
电源可以设置在浸没机柜210的外部，浸没机柜210上开设有电能输入口2101；电源模块30与导流结构20之间通过电源线连接；电能输入口2101供电源线穿入至浸没机柜210内。电源模块30连接至汇流装置40。电源线与电能输入口2101之间需要进行密封，以避免冷却液外溢。
冷却液在浸没机柜210内吸收了主板10上电子器件11的热量后会通过出液口2102流出，通过外部的冷却设备220冷却后，通过浸没机柜210内的进液口2103回流至浸没机柜210内。
请继续参阅图18，对于在单相浸没式液冷，设置在浸没机柜210外的冷却装置220可以包括循环泵、换热器以及循环管路。浸没机柜210内的冷却液可以是电子氟化液，只是电子氟化液保持液体状态。主板10直接浸没在电子氟化液中，热量从主板10上的电子器件11传递到冷却液中。
冷却装置220可以包括循环泵和换热器。在浸没机柜210的柜体上的出液口2103，循环泵、换热器、进液口2102、通过管路形成循环回路。温度较高的电子氟化液从出液口2103流出，在循环泵的动力作用在循环回路内流动，并通过在换热器内与冷却水进行热交换，从而形成温度较低的电子氟化液，温度较低的电子氟化液进而通过进液口2102回流至浸没机柜210内。在此换热器内的循环冷却水可以由冷却水塔和/或干式冷却器提供。
本实施例中浸没式液冷计算设备200基于液冷高效的散热能力，以及本申请实施例高供电密度的供电架构，突破了传统板内供电的瓶颈，从而可以允许在主板10上设置至少四个处理器115以及附属的插座、散热器113以及内存114，实现算力密度的提高的同时，保证对主板10上大功率器件的供电能力以及供电稳定性。
请参阅图19，图19是根据本申请实施例示出的一种两相浸没式液冷计算设备的示意图。对于两相浸没式液冷，进液口2103和出液口2102可以是同一个。浸没机柜210内的冷却液可以为电子氟化液。冷却 装置220包括设置在浸没机柜210外的冷凝盘管以及干式冷却器。主板10上的电子器件11直接浸没在电子氟化液中，热量从电气器件11传递到电子氟化液中，并引起电子氟化液沸腾产生蒸汽。通过电子氟化液的沸腾及冷凝过程，大幅提高传热效率。蒸汽自浸没机柜210的出液口2102流出至冷凝盘管，在冷凝盘管内与干式冷却器提供的循环流动的冷却水进行热交换，蒸汽经过冷凝转变为液态后仍然通过该出液口2102回流至浸没机柜210内。
虽然已参照几个典型实施方式描述了本发明，但应当理解，所用的术语是说明和示例性、而非限制性的术语。由于本发明能够以多种形式具体实施而不脱离发明的精神或实质，所以应当理解，上述实施方式不限于任何前述的细节，而应在随附权利要求所限定的精神和范围内广泛地解释，因此落入权利要求或其等效范围内的全部变化和改型都应为随附权利要求所涵盖。

Claims (23)

  1. 一种计算节点，其特征在于，包括：
    主板，所述主板的第一表面上安装有电子器件；沿所述主板的厚度方向开设有通流孔，所述通流孔的孔壁具有导电介质；所述通流孔与所述电子器件电连接；
    导流结构，所述导流结构供电源连接，用于传输自所述电源输出的供电电流；所述导流结构设置于所述主板的一侧，且与所述通流孔的孔壁电连接，从而沿所述主板的厚度方向将所述供电电流传输至所述通流孔内。
  2. 根据权利要求1所述的计算节点，其特征在于，所述主板内包括沿所述主板横切方向延伸的载流层；所述载流层与所述通流孔的孔壁电连接；
    所述通流孔与所述电子器件电连接，包括：所述通流孔通过所述载流层与至少一个所述电子器件电连接。
  3. 根据权利要求2所述的计算节点，其特征在于，所述通流孔有多个，所述多个通流孔中包括第一通流孔，所述第一通流孔沿所述主板的厚度方向贯穿所述主板；
    所述第一通流孔的孔壁与所述载流层接触，用于实现电连接。
  4. 根据权利要求1-3任意一项所述的计算节点，其特征在于，所述电子器件中包括处理器模块；所述通流孔有多个，多个所述通流孔中包括第二通流孔；所述主板内还包括高导部；
    所述第二通流孔沿所述主板的厚度方向延伸，所述第二通流孔的第一孔口供所述导流结构连接；所述第二通流孔的第二孔口与所述高导部连接；
    所述高导部自所述第二孔口沿所述主板的厚度方向延伸至所述主板的第一表面，并与所述处理器模块的供电端接触。
  5. 根据权利要求4所述的计算节点，其特征在于，所述高导部的横截面面积大于或等于所述第二通流孔的横截面积。
  6. 根据权利要求4所述的计算节点，其特征在于，所述高导部的横截面积自所述第二通流孔的第二孔口向所述主板的第一表面方向呈渐阔设置。
  7. 根据权利要求4所述的计算节点，其特征在于，所述第二通流孔的第二孔口、所述高导部在所述载流层的第一位置处连接；
    所述载流层的第一位置处还至少与一个通流孔电连接。
  8. 根据权利要求2至7任意一项所述的计算节点，其特征在于，所述载流层包括多个第一导电层，所述第一导电层用于传导供电电流；
    多个所述第一导电层沿所述主板的横切方向排布，且多个所述第一导电层间隔设置；每个所述第一导电层与至少一个所述通流孔电连接。
  9. 根据权利要求2所述的计算节点，其特征在于，所述载流层包括一个第一导电层，所述第一导电层的面积小于所述主板的横切面积；
    所述第一导电层与所述通流孔电连接。
  10. 根据权利要求8或9所述的计算节点，其特征在于，所述载流层包括第一层和第二层，所述第一层和所述第二层沿所述主板厚度方向依次排布；
    所述第一层包括所述第一导电层，所述第二层内包括第二导电层；所述第一导电层与所述第二导电层均与所述通流孔电连接；
    所述第二导电层的厚度小于或等于第一导电层的厚度。
  11. 根据权利要求10所述的计算节点，其特征在于，所述第二导电层有一个或多个，至少一个所述第二导电层在所述第一层上的正投影，与所述第一导电层至少部分重合；且所述正投影部分重合的所述第二 导电层与所述第一导电层电连接。
  12. 根据权利要求8至11任意一项所述的计算节点，其特征在于，所述主板内还包括信号层，所述载流层和所述信号层同层设置；
    所述信号层包括一个或多个第三导电层，所述第三导电层设置在所述第一导电层的一侧，或者相邻两个第一导电层之间。
  13. 根据权利要求8至11任意一项所述的计算节点，其特征在于，所述主板内还包括接地层，所述载流层与所述接地层同层设置；
    所述接地层包括一个或多个第四导电层，所述第四导电层设置在所述第一导电层的一侧，或者设置在相邻两个所述第一导电层之间。
  14. 根据权利要求2至13任意一项所述的计算节点，其特征在于，所述主板具有背离所述第一表面的第二表面；
    所述主板内包括两个所述载流层，其中一个所述载流层靠近所述主板的第一表面设置，另一个所述载流层靠近所述主板的第二表面设置；
    所述主板内还包括至少一个功能内层，所述功能内层为信号层、电源层或者接地层中的任意一种或多种。
  15. 根据权利要求1至14任意一项所述的计算节点，其特征在于，所述导流结构包括一个或多个导流条；
    所述导流条沿所述主板的长度方向、宽度方向或对角线方向中任意一个方向延伸。
  16. 根据权利要求1至15任意一项所述的计算节点，其特征在于，所述导流结构包括多个层叠设置的导流片，以及夹设在相邻两层导流片之间的防腐蚀层。
  17. 根据权利要求1至16任意一项所述的计算节点，其特征在于，所述主板有多个，多个所述主板中包括第一主板和第二主板；所述第二主板位于所述第一主板的一侧，且所述第一主板的第一表面和所述第二主板的第一表面朝向同一方向；
    所述导流结构包括第一导流条和第一连接条，所述第一导流条设置在所述第一主板的一侧，且与所述第一主板的通流孔固定连接；
    所述第一连接条的一端与所述第一导流条固定连接，所述第一连接条的另一端与所述第二主板的通流孔连接。
  18. 根据权利要求1至16任意一项所述的计算节点，其特征在于，所述主板有多个，多个所述主板中包括第三主板和第四主板；
    所述第三主板与所述第四主板相邻设置，且所述第三主板的第一表面和所述第四主板的第一表面分别朝向相对的两侧；
    所述导流结构夹设在所述第三主板和所述第四主板之间，且分别与所述第三主板的通流孔和所述第四主板的通流孔固定连接。
  19. 根据权利要求1所述的计算节点，其特征在于，所述主板上包括多个计算单元，每个计算单元包括处理器、设置与所述处理器一侧的内存条，以及散热器；
    所述计算单元在所述主板上呈阵列排布或者依次排列。
  20. 根据权利要求1所述的计算节点，其特征在于，所述计算节点还包括汇流装置；
    所述汇流装置上具有多个电能输入部以及电能输出部；每个电能输入部与所述电源连接，所述电能输出部与所述导流结构连接。
  21. 一种计算设备，其特征在于，包括壳体，以及如权利要求1至20任意一项所述的计算节点；所述计算节点安装在所述壳体内。
  22. 根据权利要求21所述的计算设备，其特征在于，所述计算设备还包括浸没机柜以及开设在所述浸没机柜上的电能输入口、出液口和进液口；所述浸没机柜内容置有冷却液，所述计算节点浸没于所述冷却液中；
    所述电源设置在所述浸没机柜的外部；所述电源与所述导流结构之间通过电源线连接；所述电能输入口供所述电源线穿入所述浸没机柜内；
    所述出液口供气态或者液态的冷却液流出，冷却后的所述冷却液通过所述进液口回流至所述浸没机柜内。
  23. 根据权利要求22所述的计算设备，其特征在于，所述计算设备内包括多个平行设置的导流结构，每个所述导流结构用于为一个或多个主板供电；
    所述计算设备还包括汇流装置，所述汇流装置呈条状，且沿所述多个导流结构的排布方向延伸；每个所述导流结构固定连接至汇流装置上。
PCT/CN2023/098055 2022-08-30 2023-06-02 计算节点及计算设备 WO2024045735A1 (zh)

Applications Claiming Priority (2)

Application Number Priority Date Filing Date Title
CN202211049239.9 2022-08-30
CN202211049239.9A CN115500008A (zh) 2022-08-30 2022-08-30 计算节点及计算设备

Publications (2)

Publication Number Publication Date
WO2024045735A1 true WO2024045735A1 (zh) 2024-03-07
WO2024045735A9 WO2024045735A9 (zh) 2024-05-10

Family

ID=84466170

Family Applications (1)

Application Number Title Priority Date Filing Date
PCT/CN2023/098055 WO2024045735A1 (zh) 2022-08-30 2023-06-02 计算节点及计算设备

Country Status (2)

Country Link
CN (1) CN115500008A (zh)
WO (1) WO2024045735A1 (zh)

Families Citing this family (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN115500008A (zh) * 2022-08-30 2022-12-20 超聚变数字技术有限公司 计算节点及计算设备

Citations (7)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US20060050494A1 (en) * 2004-09-03 2006-03-09 Cotek Electronic Ind. Co. Ltd. DC-AC power inverter
CN201550356U (zh) * 2009-11-20 2010-08-11 陈赞棋 能负载大电流的电路板
CN110556642A (zh) * 2019-09-29 2019-12-10 上海泽丰半导体科技有限公司 载流结构
CN111065199A (zh) * 2019-11-29 2020-04-24 华为技术有限公司 一种供电装置及单板
CN114916127A (zh) * 2021-02-09 2022-08-16 苏州旭创科技有限公司 电路板及其制造方法
CN115500008A (zh) * 2022-08-30 2022-12-20 超聚变数字技术有限公司 计算节点及计算设备
CN115756134A (zh) * 2022-11-17 2023-03-07 超聚变数字技术有限公司 一种计算设备

Family Cites Families (8)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
JP2808958B2 (ja) * 1992-01-07 1998-10-08 三菱電機株式会社 配線基板及びその製造方法
JPH07297359A (ja) * 1993-08-05 1995-11-10 Fujitsu Ltd マルチチップモジュールとマルチチップモジュール用コネクタ
CN102759974A (zh) * 2011-04-26 2012-10-31 鸿富锦精密工业（深圳）有限公司 计算机主板
CN202121870U (zh) * 2011-06-24 2012-01-18 鸿富锦精密工业（深圳）有限公司 电路板
US9144179B2 (en) * 2013-02-01 2015-09-22 Dell Products, L.P. System and method for powering multiple electronic devices operating within an immersion cooling vessel
JP2019102532A (ja) * 2017-11-29 2019-06-24 三菱電機株式会社 バスバー基板、プリント配線装置及び電力変換装置
CN113301764B (zh) * 2020-06-30 2023-07-18 阿里巴巴集团控股有限公司 一种机柜、浸没液冷系统及浸没式液冷方法
CN113498252B (zh) * 2020-10-09 2022-07-12 景旺电子科技(龙川)有限公司 电子设备、线路板及其制备方法

Patent Citations (7)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US20060050494A1 (en) * 2004-09-03 2006-03-09 Cotek Electronic Ind. Co. Ltd. DC-AC power inverter
CN201550356U (zh) * 2009-11-20 2010-08-11 陈赞棋 能负载大电流的电路板
CN110556642A (zh) * 2019-09-29 2019-12-10 上海泽丰半导体科技有限公司 载流结构
CN111065199A (zh) * 2019-11-29 2020-04-24 华为技术有限公司 一种供电装置及单板
CN114916127A (zh) * 2021-02-09 2022-08-16 苏州旭创科技有限公司 电路板及其制造方法
CN115500008A (zh) * 2022-08-30 2022-12-20 超聚变数字技术有限公司 计算节点及计算设备
CN115756134A (zh) * 2022-11-17 2023-03-07 超聚变数字技术有限公司 一种计算设备

Also Published As

Publication number Publication date
CN115500008A (zh) 2022-12-20
WO2024045735A9 (zh) 2024-05-10

Similar Documents

Publication Publication Date Title
US7978472B2 (en) Liquid-cooled cooling apparatus, electronics rack and methods of fabrication thereof
US7405936B1 (en) Hybrid cooling system for a multi-component electronics system
US7639498B2 (en) Conductive heat transport cooling system and method for a multi-component electronics system
US7916483B2 (en) Open flow cold plate for liquid cooled electronic packages
US8027162B2 (en) Liquid-cooled electronics apparatus and methods of fabrication
US8194406B2 (en) Apparatus and method with forced coolant vapor movement for facilitating two-phase cooling of an electronic device
US9538688B2 (en) Bimodal cooling in modular server system
US8587943B2 (en) Liquid-cooling memory modules with liquid flow pipes between memory module sockets
US9253923B2 (en) Fabricating thermal transfer and coolant-cooled structures for cooling electronics card(s)
WO2024045735A1 (zh) 计算节点及计算设备
JP7288998B2 (ja) 目詰まり防止機構を有するコールドプレート
JP2019521435A (ja) コンピュータおよびデータセンタ（ｄａｔａ ｃｅｎｔｅｒ）の放熱用の作動媒体接触式冷却システム
US11516941B2 (en) Heat sink and printed circuit board arrangements for data storage systems
EP3829278B1 (en) Cooling arrangement for a server mountable in a server rack
WO2024051230A1 (zh) 服务器和机柜服务器
WO2024066440A1 (zh) 计算节点和服务器
JP2013069087A (ja) 電子部品の実装構造
CN212276359U (zh) 一种液冷散热装置及液冷虚拟货币挖矿机
WO2024001749A1 (zh) 一种光模块的液冷结构及光模块
TWM638361U (zh) 電腦系統、其節點組件及其電腦
CN118276648A (zh) 服务器及机柜系统

Legal Events

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

Ref document number: 23858774

Country of ref document: EP

Kind code of ref document: A1