Configurable cold plate for data center cooling systems

Abstract

A configurable cold plate for a data center cooling system is disclosed, in particular a configurable cold plate for a data center liquid cooling system. The cold plate comprises a first portion, a second portion and an intermediate layer, the intermediate layer being variable and having a first passage enabling coolant to flow through the intermediate layer, and having a second passage or at least one adapted second passage for concentrating coolant or coolant flow to at least one area within the configurable cold plate, the area corresponding to at least a heat generating feature of an associated computing device.

Description

TECHNICAL FIELD

[0001] At least one embodiment relates to a cold plate configured for and used in a data center liquid cooling system. In at least one embodiment, the cold plate has a first portion, a second portion, and an intermediate layer that is exchangeable and has a first channel that supports a flow of coolant and has a second channel or at least one adapted second channel for concentrating coolant or a flow of coolant to at least one area within the cold plate. BACKGROUND

[0002] Data center cooling systems often use fans to circulate air in server assemblies. Certain supercomputers or other high-capacity computers can use water or other cooling systems instead of air cooling systems to draw heat away from server assemblies or racks in a data center to an area outside the data center. The cooling system can include chillers within the data center area, including the area outside the data center. The area outside the data center can be an area that includes a cooling tower or other external heat exchanger that receives heated coolant from the data center and dissipates heat to the environment (or external cooling medium) through forced air or other means before the cooled coolant is recirculated back to the data center. In an example, the chillers and cooling tower together form a cooling plant, where a pump is responsive to a temperature measured by an external device applied to the data center. A separate air cooling system can not be able to absorb enough heat to support effective or efficient cooling in the data center, and a liquid cooling system can not be able to distribute coolant effectively or efficiently. BRIEF DESCRIPTION OF DRAWINGS

[0003] Various embodiments according to the present disclosure will be described in reference to the drawings, wherein:

[0004] Figure 1 is a block diagram of an example data center with an improved cooling system subject to the improvements described in at least one embodiment;

[0005] Figure 2A is a block diagram illustrating server-level features associated with a configurable cold plate for a data center liquid cooling system, according to at least one embodiment;

[0006] Figure 2B is a block diagram illustrating assembly-level features associated with a configurable cold plate for a data center liquid cooling system, according to at least one embodiment;

[0007] Figure 3A is a diagram illustrating a perspective view of a first portion and a second portion of a configurable cold plate for a data center liquid cooling system, according to at least one embodiment;

[0008] Figure 3BFIG. 1 is a plan view showing a middle layer of a configurable cold plate for a data center liquid cooling system, according to at least one embodiment;

[0009] Figure 3C FIG. 2 is a plan view showing a middle layer of a configurable cold plate for a data center liquid cooling system, according to at least one embodiment;

[0010] Figure 3D FIG. 3 is a plan view showing a first portion of a configurable cold plate for a data center liquid cooling system and an associated middle layer, according to at least one embodiment;

[0011] Figure 3E FIG. 4 is a plan view showing another first portion of a configurable cold plate for a data center liquid cooling system and another associated middle layer, according to at least one embodiment;

[0012] Figure 4 FIG. 5 is a block diagram showing rack-level features associated with a configurable cold plate for a data center liquid cooling system, according to at least one embodiment;

[0013] Figure 5A FIG. 6 is a process flow of steps of a method usable to manufacture a configurable cold plate using Figures 2A-4 FIG. 7 is a process flow of steps of a method usable to manufacture a configurable cold plate using

[0014] Figure 5B FIG. 8 is a process flow of steps of a method usable to manufacture a configurable cold plate using Figures 2A-4 FIG. 9 is a process flow of steps of a method usable to manufacture a configurable cold plate using

[0015] Figure 6 FIG. 10 shows an example data center in which at least one embodiment from Figures 2A-5B FIG. 11 shows an example data center in which at least one embodiment from DETAILED DESCRIPTION

[0016] Air cooling of high-density servers can be inefficient or ineffective due to sudden high heat demands caused by varying computing loads in today’s computing components. However, since requirements vary or tend to range from minimal to maximal different cooling demands, appropriate cooling systems must be used to meet these requirements in an economical manner. For medium to high cooling demands, liquid cooling systems can be used. Different cooling demands also reflect different thermal profiles of data centers. In at least one embodiment, heat generated from components, servers, and racks is cumulatively referred to as a thermal profile or cooling demand, since the cooling demand must fully address the thermal profile. In at least one embodiment, a thermal profile or cooling demand of a cooling system is the heat or cooling demand generated by a component, server, or rack associated with the cooling system, and can be part of a component, server, and rack of a data center.

[0017] In at least one embodiment, a configurable and cold plate for a data center liquid cooling system is disclosed. The cold plate addresses the design lag of liquid-cooled cold plates that can be standardized and can not be configured to effectively and efficiently remove sufficient heat from an associated computing or data center device, such as a graphics processing unit (GPU), a switch, a dual in-line memory module (DIMM), or a central processing unit (CPU). Further, the associated computing or data center device can be a processing card having one or more GPUs, switches, or CPUs thereon. Each of the GPUs, switches, and CPUs can be a heat-generating feature of the computing device. In at least one embodiment, the GPU, CPU, or switch can have one or more cores, and each core can be a heat-generating feature. The present disclosure can improve the ability of the cold plate to remove heat, where, in at least one embodiment, channels (or microchannels) are disposed in an intermediate layer between a first portion and a second portion of the cold plate to concentrate coolant or coolant flow through the cold plate. In at least one embodiment, concentrating the coolant or coolant flow through the cold plate can increase surface area for concentrated heat or heat transfer from the material of the intermediate layer (and thus to the cold plate) to the coolant.

[0018] In at least one embodiment, the configurable and cold plate for a data center liquid cooling system includes a first portion, a second portion, and an intermediate layer. In at least one embodiment, the intermediate layer is changeable from other intermediate layers and removably positioned within the first portion and the second portion, which can then be hermetically sealed together using a provided clamp. Each intermediate layer has first channels that enable coolant flow to flow through the intermediate layer, and has second channels or at least one adapted second channel for concentrating coolant or coolant flow to at least one area within the cold plate. In at least one embodiment, the at least one adapted second channel has a different size or pattern from the individual first channels. The different size or pattern enables the at least one adapted second channel to expose more surface area to the coolant within the at least one adapted second channel than the individual first channels.

[0019] In at least one embodiment, the adaptation of the at least one adapted second channel is a wave structure or dimples throughout the at least one adapted second channel, even though the at least one adapted second channel has a similar size to the individual first channels. The wave structure or dimples enable a larger surface area of the material of the intermediate layer to contact the coolant and transfer heat to the coolant, as compared to a planar or flat surface as in the case of the individual first channels. In at least one embodiment, the adaptation is a material adaptation, where the material in the at least one adapted second channel is different from the material of the first channels and is capable of transferring more heat to the coolant than the individual first channels.

[0020] In at least one embodiment, the second channels or at least one adapted second channel is located in the middle layer to correspond to at least one heat generating feature of the associated computing device. Thus, in at least one embodiment, it is possible to determine the cooling requirements of the associated computing device based in part on the location of the heat generating features (e.g., CPU, GPU, or switch); then, when the middle layer is hermetically sealed in the cold plate, the middle layer is machined or selected to have second channels or at least one adapted second channel in the area corresponding to the heat generating features.

[0021] In at least one embodiment, the size of the channels differs at least from the size of their cross-section. In at least one embodiment, the channels are implemented by grooves. In at least one embodiment, the first channels direct the coolant, while one or more second channels are adapted to have at least one size different from the first channels, where the different size ensures that more coolant passes through the second channels or flows faster than in the first channels. In at least one embodiment, the different at least one size also enables more surface area within the second channels to exchange more heat from the material of the cold plate in the second channels to the coolant relative to the first channels. In at least one embodiment, the grooves enable faster flow rates at least by reduced cross-sections to force the coolant to flow from one first channel to another first channel at a higher flow rate, such that the incoming coolant flows through the first channels at a first flow rate, through the second channels at a second flow rate, and out of the cold plate at the second flow rate or slower. In at least one embodiment, the reduced cross-sections also enable more material to form surface areas to contact more of the coolant and thus transfer more heat to the coolant.

[0022] In at least one embodiment, the size of the channels or the placement of the grooves to serve as channels increases the heat transfer surface area within the cavity of the cold plate. This can be the case of the provided fluid (e.g., coolant) inlet temperature and its flow rate. Thus, in at least one embodiment, the second channels enable the coolant to concentrate in areas within the cold plate that have more heat transfer surface area by the size or the grooves. In at least one embodiment, the concentration of the coolant refers to the concentration of heat or heat transfer surface area within the second channels over the first channels. The present application proposes a unique method of increasing the heat dissipation capacity of a cold plate by changing the microchannel design and placement in a generic cold plate design.

[0023] In at least one embodiment, each cold plate is comprised of a first portion, which can be an upper portion with an inlet and an outlet for fluid (e.g. coolant) for an auxiliary cooling loop. Each cold plate is comprised of a second portion, which can be a lower portion that mates hermetically with the first portion. In at least one embodiment, gaskets are provided in one or more of the first and second portions to achieve a hermetic seal. Fluid flow channels or microchannels are provided in different configurations or adaptations of the intermediate layer to concentrate the coolant flow or coolant in different areas of the intermediate layer, which translates to different areas of the cold plate when the intermediate layer is secured in the lower portion and the upper portion is sealed to the lower portion. In at least one embodiment, the seal is hermetic, but also removable to enable replacement of the intermediate layer. In at least one embodiment, the intermediate layer is comprised of multiple portions, where a first channel forms one portion that can be first removably inserted into the lower portion, while a second channel or second channel of a second adaptation is a second portion to be removably inserted into the lower portion in a second step.

[0024] In at least one embodiment, the selection of microchannels or channels inside the cavities of one or more of the two portions is made from portions that have already been available for a unique design of a variety of different computing devices. In at least one embodiment, the microchannels or channels are specially machined for the computing device. In at least one embodiment, machining includes drilling, forming, computer-aided machining, growing, or printing. The unique design of the intermediate layer or portions thereof for the cooling plate enables removal of a desired amount of heat and provides a final pressure drop achieved in the coolant flow that is an acceptable pressure drop to address the cooling needs of the computing device. In at least one embodiment, the selection or machining of the microchannels or channels can include selection of material, surface finish, and angle of the surface or cross-section of the channels (e.g. straight, waviness, width / height) to create the required flow characteristics for any amount of inlet flow, different inlet fluid temperature, fluid chemistry, and rated pressure drop.

[0025] Figure 1is a block diagram of an example data center 100 with a cooling system subject to the improvements described in at least one embodiment. The data center 100 can be one or more rooms 102 with racks 110 and ancillary equipment to house one or more servers on one or more server trays. The data center 100 is supported by a cooling tower 104 located outside of the data center 100. The cooling tower 104 dissipates heat from the interior of the data center 100 by acting on a primary cooling loop 106. In addition, a cooling distribution unit (CDU) 112 is used between the primary cooling loop 106 and a secondary or auxiliary cooling loop 108 to enable heat to be extracted from the secondary or auxiliary cooling loop 108 to the primary cooling loop 106. In one aspect, the auxiliary cooling loop 108 can have various ducts directly plumbed into the server trays as needed. The loops 106, 108 are shown as line diagrams, but one of ordinary skill will recognize that one or more duct features can be used. In one case, flexible polyvinyl chloride (PVC) tubing can be used with associated ducts to move fluid along each of the loops 106, 108. In at least one embodiment, one or more coolant pumps can be used to maintain a pressure differential within the loops 106, 108 to enable coolant to move according to temperature sensors at different locations, including within the room, in one or more racks 110, and / or in server enclosures or server trays within the racks 110.

[0026] In at least one embodiment, the coolant in the primary cooling loop 106 and the secondary cooling loop 108 can be at least water and an additive, such as ethylene or propylene glycol. In operation, each of the primary cooling loop and the secondary cooling loop has its own coolant. In an aspect, the coolant in the secondary cooling loop can be dedicated to the needs of the components in the server trays or racks 110. The CDU 112 is capable of independently or simultaneously fine control of the coolant in the loops 106, 108. For example, the CDU can be adapted to control the flow rate, thereby appropriately distributing the coolant to extract the heat generated within the racks 110. Further, more flexible tubing 114 is provided from the secondary cooling loop 108 to enter each server tray and provide coolant to the electrical and / or computing components. In this disclosure, electrical and / or computing components are used interchangeably to refer to heat generating components that benefit from the present data center cooling system. The tubing 118 that forms part of the secondary cooling loop 108 can be referred to as a room manifold. Separately, the tubing 116 that extends from the tubing 118 can also be part of the secondary cooling loop 108, but can be referred to as a row manifold. The tubing 114 that enters the racks as part of the secondary cooling loop 108, but can be referred to as a rack cooling manifold. Further, the row manifold 116 extends along a row to all of the racks in the data center 100. The tubing of the secondary cooling loop 108, including the manifolds 118, 116, and 114, can be improved by at least one embodiment of the present disclosure. An optional chiller 120 can be provided in the primary cooling loop within the data center 102 to support cooling before the cooling tower. In terms of the presence of an additional loop in the primary control loop, one of ordinary skill reading the present disclosure will recognize that the additional loop provides cooling outside of the racks and outside of the secondary cooling loop; and can be used with the primary cooling loop for the present disclosure.

[0027] In at least one embodiment, in operation, heat generated within the server trays of rack 110 can be transferred to coolant exiting rack 110 via flexible tubing of exhaust manifold 114 of secondary cooling loop 108. Relatedly, secondary coolant from CDU 112 for cooling rack 110 (in secondary cooling loop 108) moves toward rack 110. Secondary coolant from CDU 112 is delivered from one side of room manifold with tubing 118 to one side of rack 110 via exhaust manifold 116 and through tubing 114 by one side of server trays. Used secondary coolant (or heat carrying secondary coolant exiting computing components) exits from another side of server trays (e.g., into left side of rack of server trays and exits from right side of rack after circulating through server trays or components on server trays). Used secondary coolant exiting server trays or rack 110 comes out from a different side (e.g., exit side) of tubing 114 and moves to a parallel but also exit side of exhaust manifold 116. From exhaust manifold 116, used secondary coolant moves in a direction opposite to incoming secondary coolant (which can also be newer secondary coolant) in a parallel portion of room manifold 118 and toward CDU 112.

[0028] In at least one embodiment, used secondary coolant exchanges its heat with primary coolant in primary cooling loop 106 via CDU 112. Used secondary coolant is refreshed (e.g., relatively cooled when compared to temperature at used coolant) and ready to be circulated back to computing components by secondary cooling loop 108. Various flow and temperature control features in CDU 112 enable control of heat exchanged from used secondary coolant or flow of secondary coolant into and out of CDU 112. CDU 112 is also able to control flow of primary coolant in primary cooling loop 106.

[0029] In at least one embodiment, cold plates herein support variations in power and thermal characteristics of various computing components by merely replacing the middle layer, without requiring new cold plates. Thus, in at least one embodiment, cold plates herein enable a universal cold plate with the ability to track variations in computing components, but also with the ability to allow replacement of internal heat transfer components or chemical composition of fluid, which can impact performance of the cold plate if not replaced for different channel sizes, which can compensate for these variations. Further, the ability to alter the middle layer enables design teams to quickly and seamlessly design and deploy liquid cooling components for servers in data center applications. Cold plates herein are also able to use a universal class of liquid cooling by at least replacing thermal characteristics of the cold plate (e.g., microchannels), which translates to modifications in cold plate design to meet and exceed data center needs.

[0030] Figure 2Ais a block diagram 200 illustrating server-level features associated with configurable cold plates for a data center liquid cooling system, according to at least one embodiment. The server-level features include a server tray or chassis 202 having at least one server manifold 204 to allow cooling fluid (e.g., coolant) to enter and exit from a rack to the server tray or chassis 202. Coolant from the rack manifold enters through an inlet pipe 206 and exits via an outlet pipe 208. The server-side coolant travels via an inlet line 210, through one or more cold plates 210A, 210B, and via an outlet line 212 to the manifold 204. This represents at least one or more cooling loops 214A, 214B within the server tray or chassis 202. In at least one embodiment, the cold plates 210A-D are associated with at least one computing component 220A-D.

[0031] In at least one embodiment, one or more of the cold plates 210A-D are configurable cold plates. In at least one embodiment, although illustrated as having one inlet and one outlet for the inlet line 210 and outlet line 212, there can be multiple intermediate lines, such as flexible tubes that associate the cold plate with the respective inlet line 210 and outlet line 212. In at least one embodiment, intermediate lines that couple the cold plate directly to the manifold 204 are provided with an inlet and an outlet for such connections. In at least one embodiment, fluid adapters are provided to enable such coupling. In at least one embodiment, the fluid adapters are sized to fit the cold plate and the inlet and outlet devices in the manifold 204.

[0032] Figure 2B is a block diagram 250 illustrating component-level features associated with configurable cold plates for a data center liquid cooling system, according to at least one embodiment. The component-level features include computing or data center equipment formed by one or more of components 252, 254. In at least one embodiment, the component 252 is a board or card, such as a printed circuit board (PCB) or printed circuit card, that is packaged and shielded to protect components therein. In at least one embodiment, the component 254 is a chip or semiconductor device, such as a CPU, GPU, or switch. In at least one embodiment, there can be multiple components mounted on the PCB 252, even though only one component 254 is illustrated. In at least one embodiment, the component 254 can include multiple dies (e.g., a multi-core processor device). In at least one embodiment, the cores can be stacked or distributed. In at least one embodiment, the components 252; 254 can have different heat generating characteristics, at least represented by the location of the dies therein. In the case of the PCB 252, when there are multiple components 254 thereon, each component can be a heat generating characteristic.

[0033] In at least one embodiment, a cold plate 258 is associated with a computer device. In at least one embodiment, the cold plate 258 is associated with a component 254.Figure 2B In the illustration of FIG. 3, cold plate 258 is associated with computing device 254. In at least one embodiment, cold plate 258 can extend across the dimensions of PCB 252 to provide direct or indirect contact cooling to one or more computing components on PCB 252. In at least one embodiment, when a graphics processing card is the computing device, cold plate 258 extends across the card, but channels therein can concentrate the flow of coolant through areas of the card having processor or memory intensive computing devices. The computing device can thus have additional computing devices associated therewith.

[0034] In at least one embodiment, cold plate 258 is associated with computing device 254 via thermal transfer layer 256. The thermal transfer layer can be a layer having one or more of silicon, a thermal interface material, or air. In at least one embodiment, there can be no thermal transfer layer 256 and bottom portion 258A can be directly associated with computing device 254. The cold plate has top portion 258B with at least one inlet for coolant inlet line 260 and at least one outlet for coolant outlet line 262. In at least one embodiment, top portion 258B is hermetically sealed with bottom portion 258A using gaskets therebetween and at least latch clip 264, although multiple latch clips can be provided across the sides of the top and bottom portions to latch the portions together. In at least one embodiment, there can be hinges on at least one side to hold the portions together during a change in the intervening layer therein.

[0035] Figure 3A is a diagram showing a perspective view 300 of a first portion 302 and a second portion 308 (bottom portion) of a configurable cold plate for a data center liquid cooling system, according to at least one embodiment. First portion 302 and second portion 308 can be associated with one or more intervening layers, such as the intervening layer shown in FIG. 3. In at least one embodiment, one or more gaskets are associated with at least the first portion or the second portion to achieve a hermetic seal when the first portion and the second portion are closed together. In at least one embodiment, latch clips formed by the two sides, latch receiver 310A and latch 310B, achieve a hermetic seal by holding the portions together. Figure 3B

[0036] In at least one embodiment, fluid adapters 304, 306 extend from the configurable cold plate to enable connection of the cold plate to at least a cooling manifold (e.g., cooling manifold 202 of FIG. 2) and a cooling loop (e.g., cooling loop 204 of FIG. 2). In at least one embodiment, fluid adapters 304, 306 are associated with the first portion 302 and the second portion 308, respectively, of the configurable cold plate. Figure 2A ​coolant between the server manifold and the intermediate layer. In at least one embodiment, the bottom portion enables a perfect fit of the intermediate layer within the bottom portion. Further, in at least one embodiment, any space for fluid to flow between the bottom portion and the intermediate layer is minimal. Indeed, in at least one embodiment, the intermediate layer can have one or more orifices within the layer (e.g. Figure 3B the server manifold into the intermediate layer without spilling into any gap between the bottom portion 208 and the intermediate layer. In at least one embodiment, coolant or other fluid flows into the inlet fluid adapter 306 and out of the outlet fluid adapter 304. In at least one embodiment, even without orifices in the intermediate layer, fluid or coolant is still enabled to flow as directed by the first and second channels of the intermediate layer.

[0037] Figure 3B is a diagram illustrating a plan view 320 of an intermediate layer 322 of a configurable cold plate for a data center liquid cooling system, in accordance with at least one embodiment. In at least one embodiment, the intermediate layer 322 is interchangeable with other intermediate layers (e.g. Figure 3D and Figure 3E illustrated in FIGS. 1-3. The intermediate layer 322 includes a first channel 326 for enabling coolant flow through the intermediate layer 322 and includes a second channel (or at least one adapted second channel) 330 for concentrating coolant or coolant flow to at least one region within the intermediate layer 322. In at least one embodiment, when the intermediate layer is in a cold plate, the concentration of coolant or coolant flow is to at least one region of the cold plate that coincides with the at least one region of the intermediate layer 322.

[0038] In at least one embodiment, there can be a second channel 330 that is different in size from the first channel 326. The different size of the second channel 330 can be to concentrate coolant or coolant flow into at least one region within the middle layer 322. In at least one embodiment, concentrating coolant or coolant flow into at least one region within the middle layer can be described by the amount of cooling provided in the at least one region relative to other regions of the middle layer, which are also regions of the cold plate when the middle layer is within the cold plate. In at least one embodiment, concentrating coolant or coolant flow into at least one region within the middle layer can be described by the amount of surface area (also referred to as heat or heat transfer surface area) exposed to coolant in the at least one region compared to other regions of the middle layer, which are also regions of the cold plate when the middle layer is within the cold plate. In at least one embodiment, concentrating coolant or coolant flow in at least one region can be described as an increase in concentration of coolant or an increase in coolant flow in the at least one region relative to other regions of the middle layer, which are also other regions of the cold plate when the middle layer is within the cold plate.

[0039] In at least one embodiment, the second channel has slots in the middle layer. Individual ones of the slots have at least one first dimension that is different relative to individual ones of the first channels and across their respective cross sections. In at least one embodiment, the diameter, width, height, or angle of the individual slots is less than the diameter, width, height, or angle of the individual first channels. In at least one embodiment, this results in a plurality of slots in the region of the second channel. The plurality of slots have walls that form side surface regions therein. The side surface regions are simply referred to as surface regions or heat transfer or heat transfer surface regions because they enable more heat to be transferred to the passing coolant. Surface regions can also be at the top and bottom of the slots. In at least one embodiment, a second middle layer can be used for each cold plate. The second middle layer is used in place of the middle layer. Individual second slots of the second middle layer can have at least one second dimension that is different from the at least one first dimension. The at least one second dimension is different from concentrating or concentrating less coolant or coolant flow into the at least one region or cold plate relative to different regions of the first middle layer.

[0040] In at least one embodiment, the coolant flow refers to a flow rate or flow volume of the coolant in at least one region of the middle layer relative to other regions. In at least one embodiment, the coolant is in a dynamic state and continuously moving through the cold plate. However, as shown in at least one embodiment, the first channels 326 can be narrower than the second channels 330. Thus, the coolant spends more time in the second channels 330 than in the first channels 326. In at least one embodiment, concentrating the coolant or coolant flow can be to slow down the flow rate of the coolant so that the coolant spends more time exchanging heat from the associated computing device in at least one region with the second channels. In at least one embodiment, concentrating the coolant or coolant flow can be to increase the flow rate of the coolant so that the coolant does not saturate from the exchanged heat from the associated computing device in at least one region with the second channels. As the coolant flows faster, it can cool the at least one region faster or achieve a faster heat exchange. In at least one embodiment, even though the second channels 330 can be wider than the first channels 326, the second channels 330 are represented by the grooves that cause a pressure gradient between the first channels 326, thereby experiencing a higher flow rate in at least one region with the second channels 330.

[0041] In at least one embodiment, the at least one adapted second channel is described by having a different size than the first channels. The second channels or at least one adapted second channel in the middle layer to at least correspond to the heat generating features of the associated computing device. In doing so, in at least one embodiment, the cold plate is configurable to maximize heat exchange from the heat generating features of the associated computing device. This represents at least an efficient and effective heat exchange process compared to a static cold plate that uses a uniform distribution of coolant. In at least one embodiment, one or more orifices (e.g., the labeled portions 324, 328 in FIG. 3B) within the middle layer 322 support the fluid adapters 304, 306, or enable a smooth flow (e.g., less than any flow that is turbulent) of the coolant from the server manifold into the middle layer 322 without spilling into any gap between the bottom portion and the middle layer 322 when the middle layer 322 is removably located within the bottom portion. Figure 3B

[0042] ​In at least one embodiment, a seal such as rubber, silicone, or inert material is provided around the orifice to substantially prevent coolant flow outside of the intermediate layer. In at least one embodiment, the fluid adapter extends into the orifice below the top portion of the cold plate and is held tightly by the seal. To replace the intermediate layer, with the top portion of the cold plate open, the intermediate layer can be pulled out and the seal can come out with the intermediate layer. In at least one embodiment, to ensure integrity, a new seal can be required for each new or different intermediate layer used. In at least one embodiment, similar seals are provided for the fluid adapters 304, 306 to enable coupling to the coolant lines from the server manifold or related cooling loop.

[0043] Figure 3C FIGS. 34A, B, C are various cross-sectional views 340A, B, C showing second channels 342A, B; 344A, B; and 346A, B (or adapted second channels) in an intermediate layer of a configurable cold plate for a data center liquid cooling system, in accordance with at least one embodiment. In at least one embodiment, the intermediate layer 322 is a sandwich structure with a top plate 348B and a bottom plate 348A separated by walls (e.g., vertical, angled, or circumferential structures forming channels). The walls can support the top plate. In at least one embodiment, only the bottom plate is present and the walls contiguous with the bottom plate provide channels that can be open at the top or can be closed by the top portion of the cold plate when the intermediate layer is located within the cold plate. The top portion of the cold plate then acts as a closure for the walls.

[0044] In at least one embodiment, the intermediate channels 332; 350 are closed or formed as additional first channels with the first channels 326 on either side of the intermediate layer 322. In at least one embodiment, when the intermediate channels 332; 350 are closed, they are formed as through holes from the plane of the intermediate layer 322 to the bottom view and blocked by walls so that coolant does not flow through the area. In at least one embodiment, the intermediate channels 332; 350 are at least one second channel that can have different dimensions to concentrate a second amount of coolant or a second coolant flow through the intermediate channels 332 relative to a first coolant concentration or a first coolant flow to the first channels 326 and second channels 330.

[0045] In at least one embodiment, the cross-sectional views 340A, B, or C can span Figure 3B , Figure 3D and Figure 3EThe middle layer of any of the embodiments of FIGS. 34A, 34B, and 34C. In at least one embodiment, the walls forming the second channels 342A, B in cross-sectional view 340A are vertical (or perpendicular relative to the top and bottom portions of the cold plate). In at least one embodiment, the walls forming the second channels 346A, B in cross-sectional view 340C are angled (relative to the top and / or bottom portions of the cold plate). In at least one embodiment, the sandwiched structure of plates 348A, B is initially a machined monolithic structure, but the channels 344A, B are formed by holes drilled through the middle of the monolithic structure along its length or width. In at least one embodiment, the channels can be circular and have a diameter as a dimension for reference.

[0046] In at least one embodiment, the walls form a slot therebetween and the slot traverses the length of the second channel or at least one adapted second channel. Further, the slot (representing the second channel) concentrates the coolant or flow of coolant to at least one region by at least flowing parallel through the slot. The walls represent additional surface area that forms an interface for heat exchange between the underlying computing device and the coolant. In at least one embodiment, the middle channel 350 is available in each of the embodiments of FIGS. 34A, 34B, and 34C. Figure 3C In at least one embodiment, a mix of walls (vertical, angled, or circumferential) can be used in different channels within a single middle layer.

[0047] Figure 3D is a diagram showing a plan view 360 of a first portion 362 of a configurable cold plate for a data center liquid cooling system and associated middle layer 368, according to at least one embodiment. As with the embodiments of FIGS. 34A, 34B, and 34C, the middle layer 368 is sandwiched between a top portion 370A and a bottom portion 370B of the cold plate. Figure 3A and Figure 3B Unlike the embodiments of FIGS. 34A, 34B, and 34C, the plan view 360 shows that there can be two inlet fluid adapters 364A, B that support coolant into the middle layer 368, and there can be two outlet fluid adapters 366A, B that support coolant out of the middle layer 368. As described with reference to FIGS. 34A, 34B, and 34C, there can be associated seals with orifices into the sandwiched structure of the middle layer 368. Alternatively, coolant flows from the fluid adapters into the middle layer and through the channels before flowing out. In at least one embodiment, the many surface areas implemented by the slots described in FIGS. 34A, 34B, and 34C are sufficient to concentrate the coolant or flow of coolant in the regions with the slots in the middle layer (and thus in the cold plate). Figure 3A -C, there can be associated seals with orifices into the sandwiched structure of the middle layer 368. Alternatively, coolant flows from the fluid adapters into the middle layer and through the channels before flowing out. In at least one embodiment, the many surface areas implemented by the slots described in FIGS. 34A, 34B, and 34C are sufficient to concentrate the coolant or flow of coolant in the regions with the slots in the middle layer (and thus in the cold plate). Figure 3C

[0048] ​In at least one embodiment, coolant enters the middle layer 368 from the inlet fluid adapters 364A,B of the top portion 362. As indicated by the arrows, the coolant flows through the one or more first channels 370, through the one or more second channels 376, out of the outlets 374A,B provided in the middle layer 368, and finally out through one of the outlet fluid adapters 366A,B. In at least one embodiment, refer to Figure 3C Any of the cross sections discussed can be applicable to the cross section of the middle layer 368.

[0049] Figure 3E is another plan view 380 showing another first portion 382 of a configurable cold plate for a data center liquid cooling system and another associated middle layer 388, in accordance with at least one embodiment. The plan view 380 shows (with Figure 3A , Figure 3B and Figure 3D embodiments) there can be only one inlet fluid adapter 384, which supports one inlet 392 of coolant to the middle layer 368, and there can be multiple outlet fluid adapters 386A,B for supporting two outlets 394A,B of coolant. These features can enable higher flow rates due to the pressure differential from higher outlet pressure (which is enabled by multiple outlets) and lower inlet pressure (from a single inlet). In at least one embodiment, knowledge of fluid dynamics for appropriate middle layer selection can be provided. In at least one embodiment, a single inlet middle layer can enable increased coolant flow rate when an existing cooling loop is experiencing low coolant pressure (such as towards the end of a line of coolant piping, last rack).

[0050] In at least one embodiment, as described with reference to Figure 3A -C, there can be associated seals with orifices into the sandwich structure of the middle layer 388 for the inlet and outlet of the middle layer. Alternatively, coolant flows into the middle layer from the fluid adapter 384 and through these channels before flowing out. In at least one embodiment, the many surface areas enabled by the walls of the channels described in Figure 3C are sufficient to concentrate coolant or coolant flow in the area of the channel with the middle layer (and thus in the cold plate). In at least one embodiment, coolant enters the middle layer 388 from the inlet fluid adapter 384 of the top portion 382. As indicated by the arrows, the coolant flows through the one or more first channels 390, through the one or more second channels, out of the outlets 394A,B provided in the middle layer 388, and finally out through one of the outlet fluid adapters 394A,B. In at least one embodiment, refer to Figure 3C Any of the cross sections discussed can be applicable to the cross section of the middle layer 388.

[0051] Figure 4 is a block diagram illustrating a rack-level feature 400 associated with a configurable cold plate of a data center liquid cooling system, according to at least one embodiment. A rack 402 has brackets 404, 406 to enable one or more cooling loop components to be hung within the rack 402. In at least one embodiment, a rack manifold 412, 414 can be provided to direct coolant from a row manifold to a server tray or bin 408 with the rack 402. The rack manifold 412 can pass coolant from the row manifold through a conduit 410, through the server tray or bin 408, out an exit row manifold 414, and back to the row manifold through an exit conduit 412. If increased pressure of the coolant flow at this level is desired, the configurable cold plate can use a higher pressure mid-layer toward the bottom server tray or bin of the illustrated server tray or bin 408. Alternatively, a high pressure mid-layer can be used in the cold plate of the top server tray or bin of the illustrated rack 402 due to the higher coolant head pressure at the bottom.

[0052] Figure 5A is a process flow of steps of a method 500 of a configurable cold plate that can be used to use Figures 2A-4 a configurable cold plate, according to at least one embodiment. Step 502 determines at least one computing component having a heat generating feature, such as a processor core or processor, switch, or memory component. In at least one embodiment, a sub-step of step 502 entails determining a region of a cold plate associated with the heat generating feature. In at least one embodiment, the region is also a reference to a location in the at least one computing device that generates the most heat during normal use of the at least one computing device. In at least one embodiment, the location that generates the most heat during saturated use of the at least one computing device is used as a basis to perform subsequent steps to select or provide a mid-layer.

[0053] Step 504 provides a cold plate having a first portion and a second portion to be hermetically and removably sealed together. Step 506 enables one or more mid-layers in the cold plate to be replaced and to concentrate coolant or coolant flow to a region of the cold plate. In at least one embodiment, step 506 includes the following sub-steps: determining a first individual mid-layer has a second channel or at least one adapted second channel to concentrate coolant or coolant flow to a first region within the cold plate; and determining a second individual mid-layer has a second channel or at least one adapted and different second channel to concentrate coolant or coolant flow to a second region within the cooling plate that is different from the first individual mid-layer. In at least one embodiment, step 506 includes the sub-step of making the mid-layers according to the requirements of the at least one computing component, as discussed with respect to method 550.

[0054] Step 508 determines whether to implement the intermediate layer from step 506 for the at least one computing device, where at least the first region corresponds to the location of the heat generating feature. In this case, step 508 enables the first individual intermediate layer’s first channel to allow coolant to flow therein and enables the second channel or at least one adapted second channel to concentrate the flow or coolant therein. In at least one embodiment, a second individual intermediate layer can be determined to be suitable for the at least one computing device and used in place of the first individual intermediate layer.

[0055] Method 500 thus enables one or more intermediate layers to be removably located within the first portion and the second portion. Method 500 enables a first individual intermediate layer of the one or more intermediate layers to be exchanged with a second individual intermediate layer. Method 500 ensures that the one or more interchangeable intermediate layers have respective first channels to enable coolant to flow therein and have respective second channels or respective at least one adapted second channel to concentrate the coolant or coolant flow within the cold plate to correspond to the heat generating feature.

[0056] In at least one embodiment, method 500 includes a further step 512 for associating the cold plate with the at least one computing component. Sub-steps can include associating an inlet coolant line with the inlet of the first portion and an outlet coolant line with the outlet of the first portion. When the coolant flow is initiated, the coolant will flow through the inlet coolant line and the inlet of the first portion, to the first channel and the second channel or at least one adapted second channel to concentrate the flow or coolant therein.

[0057] In at least one embodiment, further steps of method 500 or sub-steps of step 506 anticipate a change when it is determined during operation to change the at least one computing device by replacing it with a second computing component having a second heat generating feature. Sub-steps preempt or perform new determination steps for a second region within the cold plate associated with the second heat generating feature. In at least one embodiment, a second individual intermediate layer can pre-qualify for the second computing device because it has a second channel or at least one adapted second channel positioned differently than the first individual intermediate layer. This allows the second individual intermediate layer to concentrate the coolant or coolant flow to the second region within the cold plate.

[0058] Figure 5B is usable to manufacture a cold plate according to at least one embodiment Figures 2A-4the process flow of the steps of the method 550 of configurable cold plates. Step 552 provides a first portion of a fluid adapter having at least one inlet and at least one outlet to couple to a cooling loop. Step 554 provides a second portion to hermetically and removably seal with the first portion. In at least one embodiment, steps 552, 554 can be performed by a shaping machine, a forging machine, a casting machine, a 3-dimensional printer, or a computer numerical control (CNC) machine.

[0059] Step 556 is a machining step to machine one or more intermediate layers that are also removably located within the second portion and the first portion. In at least one embodiment, steps 552, 554 can be performed in advance, but step 556 can be performed on-demand based in part on a computing device to be cooled by the cold plate. In at least one embodiment, step 558 is performed to determine whether there are locations in the cold plate that require a concentration of coolant or a flow of coolant. This can be performed by checking the requirements of the computing device to be cooled.

[0060] When there are locations that require a concentration of coolant or a flow of coolant, step 560 is performed. In at least one embodiment, using step 560 enables individual ones of the one or more intermediate layers to have respective first channels (e.g., by machining) to allow coolant to flow therein and to have respective second channels or respective at least one adapted second channel to concentrate coolant or a flow of coolant within the respective second channels or the respective at least one adapted second channel. Since these benefits are related to the requirements of the associated computing device, this step can be performed on-demand at a data center or at an infrastructure location of the data center that is capable of hosting the machining machines in the machines described above with respect to steps 552, 554. In at least one embodiment, the intermediate layers are partially machined to fit within the second portion and to be associated with the fluid adapter of the first portion. However, the channels can be machined later, e.g., on-demand.

[0061] In at least one embodiment, a sub-step of steps 552, 554 can be to provide one or more gaskets to achieve an air-tight and removable seal between the first portion and the second portion. In at least one embodiment, another sub-step of steps 552, 554 provides one or more latching clips to achieve an air-tight and removable seal between the first portion and the second portion. In at least one embodiment, with respect to step 560, when a sub-step determines cooling requirements of the at least one computing component, at least in part determines heat generating characteristics of the at least one computing component, the following further sub-steps are performed: for drilling a first channel in one or more intermediate layers to enable coolant to flow therein; and for drilling a second channel or machining at least one adapted second channel to concentrate coolant or coolant flow within the second channel or at least one adapted second channel according to a location of the cooling requirements of the at least one computing component.

[0062] In at least one embodiment, with respect to step 560, when a sub-step determines cooling requirements of the at least one computing component, at least in part determines heat generating characteristics of the at least one computing component, a further sub-step of printing or growing one or more intermediate layers to include a first channel and a second channel or at least one adapted second channel according to a location of the cooling requirements of the at least one computing component is performed. Finally, at step 562, the bottom portion of the cold plate is cleaned and prepared for association with the at least one computing device.

[0063] Data Center

[0064] Figure 6 An example data center 600 is illustrated in which the configurable cold plates from Figures 2A-5B at least one embodiment can be used. In at least one embodiment, data center 600 includes a data center infrastructure layer 610, a framework layer 620, a software layer 630, and an application layer 640. In at least one embodiment, components associated with configurable cold plates of a data center liquid cooling system can be performed within or in cooperation with example data center 600, for example as described above with reference to Figures 2A-5B In at least one embodiment, infrastructure layer 610, framework layer 620, software layer 630, and application layer 640 can be provided, in part or in whole, via computing components located on server trays in racks 210 of data center 200. This enables the cooling systems of the present disclosure to directly cool certain of the computing components in an efficient and effective manner. Moreover, various aspects of a data center, including data center infrastructure layer 610, framework layer 620, software layer 630, and application layer 640, can be used to support the selection or design of intermediate layers of configurable cold plates as discussed above at least with reference to Figures 2A-5B In at least one embodiment, infrastructure layer 610, framework layer 620, software layer 630, and application layer 640 can be provided, in part or in whole, via computing components located on server trays in racks 210 of data center 200. This enables the cooling systems of the present disclosure to directly cool certain of the computing components in an efficient and effective manner. Moreover, various aspects of a data center, including data center infrastructure layer 610, framework layer 620, software layer 630, and application layer 640, can be used to support the selection or design of intermediate layers of configurable cold plates as discussed above at least with reference to Figure 6the discussion can be understood to apply to implementations or support for Figures 2A-5B hardware and software features required for configurable cold plates of a data center liquid cooling system of a data center for

[0065] In at least one embodiment, as Figure 6 shown in FIG. 6, data center infrastructure layer 610 can include resource orchestrator 612, grouped computing resources 614, and node computing resources (“node C.R.s”) 616(1)-616(N), where “N” represents any whole, positive integer. In at least one embodiment, node C.R.s 616(1)-616(N) can include, but are not limited to, any number of central processing units (“CPUs” or “processors”) including accelerators, field programmable gate arrays (FPGAs), graphics processors, and / or the like, memory devices (e.g., dynamic random access memory), storage devices (e.g., solid state or disk drives), network input / output (“NW I / O”) devices, network switches, virtual machines (“VMs”), power modules, cooling modules, and / or the like. In at least one embodiment, one or more node C.R.s of node C.R.s 616(1)-616(N) can be a server having one or more of above-described computing resources.

[0066] In at least one embodiment, grouped computing resources 614 can include individual groupings of node C.R.s housed within one or more racks (not shown), or housed within a number of racks (also not shown) within a data center at various geographic locations. Individual groupings of node C.R.s within grouped computing resources 614 can include groupings of computing, network, memory, or storage resources that can be configured or allocated to support one or more workloads. In at least one embodiment, several node C.R.s including CPUs or processors can be grouped within one or more racks to provide computing resources to support one or more workloads. In at least one embodiment, one or more racks can also include any quantity of power modules, cooling modules, and network switches, in any combination.

[0067] In at least one embodiment, resource orchestrator 612 can configure or otherwise control one or more node C.R.s 616(1)-616(N) and / or grouped computing resources 614. In at least one embodiment, resource orchestrator 612 can include a software design infrastructure (“SDI”) management entity for data center 600. In at least one embodiment, resource orchestrator can comprise hardware, software, or some combination thereof.

[0068] In at least one embodiment, as Figure 6As shown, the framework layer 620 includes a job scheduler 622, a configuration manager 624, a resource manager 626, and a distributed file system 628. In at least one embodiment, the framework layer 620 can include a framework that supports software 632 of a software layer 630 and / or one or more applications 642 of an application layer 640. In at least one embodiment, software 632 or applications 642 can include web-based service software or applications, respectively, such as services or applications provided by Amazon Web Services, Google Cloud, and Microsoft Azure. In at least one embodiment, the framework layer 620 can be, but is not limited to, a type of free and open-source software web application framework such as Apache Spark™ (hereinafter “Spark”) that can utilize the distributed file system 628 for large-scale data processing (e.g., “big data”). In at least one embodiment, the job scheduler 622 can include a Spark driver to facilitate scheduling workloads supported by various layers of the data center 600. In at least one embodiment, the configuration manager 624 can be capable of configuring different layers, such as the software layer 630 and the framework layer 620 including Spark and the distributed file system 628 for supporting large-scale data processing. In at least one embodiment, the resource manager 626 can be capable of managing clustered or grouped computing resources mapped to or allocated for supporting the distributed file system 628 and the job scheduler 622. In at least one embodiment, the clustered or grouped computing resources can include the grouped computing resources 614 on the data center infrastructure layer 610. In at least one embodiment, the resource manager 626 can coordinate with the resource orchestrator 612 to manage these mapped or allocated computing resources.

[0069] In at least one embodiment, the software 632 included in the software layer 630 can include software used by at least a portion of the node C.R.s 616(1)-616(N), the grouped computing resources 614, and / or the distributed file system 628 of the framework layer 620. One or more types of software can include, but are not limited to, Internet web page search software, email virus scanning software, database software, and streaming video content software.

[0070] In at least one embodiment, one or more applications 642 included in application layer 640 can include one or more types of applications used by at least portions of node C.R.s 616(1)-616(N), grouped computing resources 614, and / or distributed file system 628 of framework layer 620. One or more types of applications can include, but are not limited to, any number of genomics applications, cognitive computing and machine learning applications including training or inferencing software, machine learning framework software (e.g., PyTorch, TensorFlow, Caffe, etc.), or other machine learning applications used in conjunction with one or more embodiments.

[0071] In at least one embodiment, any of configuration manager 624, resource manager 626, and resource orchestrator 612 can implement any number and type of self-modifying actions based on any amount and type of data acquired in any technically feasible fashion. In at least one embodiment, self-modifying actions can relieve data center operators of data center 600 from making possibly poor configuration decisions and can avoid underutilized and / or poorly performing portions of a data center.

[0072] In at least one embodiment, data center 600 can include tools, services, software, or other resources to train one or more machine learning models or use one or more machine learning models to predict or infer information in accordance with one or more embodiments herein. In at least one embodiment, machine learning models can be trained by computing weight parameters according to a neural network architecture using software and computing resources described above with respect to data center 600. In at least one embodiment, using weight parameters computed through one or more training techniques described herein, trained machine learning models corresponding to one or more neural networks can be used to infer or predict information using resources described above with respect to data center 600. Deep learning can be advanced using any appropriate learning network and computing power of data center 600. Thus, in this manner, a deep neural network (DNN), recurrent neural network (RNN), or convolutional neural network (CNN) can be supported simultaneously or concurrently using hardware in a data center. For example, once a network has been trained and successfully evaluated to identify data in a subset or slice, the trained network can provide similar representational data to be used with collected data.

[0073] In at least one embodiment, data center 600 can use CPUs, application specific integrated circuits (ASICs), GPUs, FPGAs, or other hardware to perform training and / or inference using resources described above. Moreover, one or more software and / or hardware resources described above can be configured as a service to allow users to train or perform inferencing on information, such as pressure, flow rate, temperature, and location information or other artificial intelligence services.

[0074] Inference and training logic

[0075] Inference and / or training logic 615 can be used to perform inferencing and / or training operations associated with one or more embodiments. In at least one embodiment, inference and / or training logic 615 can be used in a system Figure 6 on which neural network training operations are performed to infer or predict operations based, at least in part, on weight parameters calculated using neural network training operations, neural network functions and / or architectures, or neural network use cases herein. In at least one embodiment, inference and / or training logic 615 can include, without limitation, hardware logic in which computational resources are dedicated or otherwise uniquely used in conjunction with weight values or other information corresponding to one or more layers of neurons within a neural network. In at least one embodiment, inference and / or training logic 615 can be used in conjunction with an application specific integrated circuit (ASIC), such as Tensor Processing Units from Google, Inference Processing Units (IPUs) from Graphcore TM , or Nervana (“Lake Crest”) processors from Intel Corp.

[0076] In at least one embodiment, inference and / or training logic 615 can be used in conjunction with central processing unit (CPU) hardware, graphics processing unit (GPU) hardware, or other hardware, such as field programmable gate arrays (FPGAs). In at least one embodiment, inference and / or training logic 615 includes, without limitation, code and / or data storage models that can be used to store code (e.g., graph code), weight values, and / or other information, including bias values, gradient information, momentum values, and / or other parameter or hyperparameter information. In at least one embodiment, each code and / or data storage model is associated with a dedicated computational resource. In at least one embodiment, a dedicated computational resource includes computational hardware that further includes one or more ALUs that only perform mathematical functions (e.g., linear algebra functions) on information stored in a code and / or data storage model and stores results of those functions in an active storage model of inference and / or training logic 615.

[0077] Other variations are within the spirit of this disclosure. Therefore, although the disclosed technology is readily adaptable to various modifications and alternative constructions, certain embodiments thereof are illustrated in the accompanying drawings and have been described in detail above. However, it should be understood that the disclosure is not intended to be limited to one or more specific forms disclosed, but rather, it is intended to cover all modifications, alternative constructions, and equivalents falling within the spirit and scope of this disclosure as defined in the appended claims.

[0078] Unless otherwise stated or obviously contradicted by the context, the terms “a,” “an,” and “the,” and similar references, used in the context of describing the disclosed embodiments (particularly in the context of the appended claims), should be interpreted as encompassing both singular and plural forms, rather than as definitions of the terms. Unless otherwise stated, the terms “comprising,” “having,” “including,” and “containing” should be interpreted as open-ended terms (meaning “including, but not limited to”). The term “connection” (referring to a physical connection where not modified) should be interpreted as partially or wholly contained, attached to, or joined together, even with some intervention. Unless otherwise indicated herein, references to numerical ranges herein are intended only as a way of abbreviating each individual value falling within that range, and each individual value is incorporated into the specification as if it were separately described herein. Unless otherwise indicated or contradicted by the context, the use of the terms “set” (e.g., “item set”) or “subset” should be interpreted as a non-empty set comprising one or more members. Furthermore, unless otherwise stated or contradicted by the context, a “subset” of the corresponding set does not necessarily mean an appropriate subset of the corresponding set, but rather the subset and the corresponding set can be equal.

[0079] Unless explicitly stated otherwise or clearly contradicted by the context, conjunctions such as “at least one of A, B, and C” or “at least one of A, B, and C” are understood in context to generally refer to items, terms, etc., which can be A or B or C, or any non-empty subset of the set A, B, and C. For example, in an illustrative example of a set with three members, the conjunctions “at least one of A, B, and C” and “at least one of A, B, and C” refer to any of the following sets: {A}, {B}, {C}, {A, B}, {A, C}, {B, C}.

[0080] {A, B, C}. Therefore, this connective language is not intended to imply that certain embodiments require the presence of at least one of A, at least one of B, and at least one of C. Additionally, unless otherwise stated or contradicted by the context, “multiple” indicates a plural state (e.g., “multiple items” means multiple items). A plural is at least two items, but more may be indicated if explicitly stated or by the context. Furthermore, unless otherwise stated or clearly understood from the context, “based on” means “at least partially based on” rather than “based on only.”

[0081] Unless otherwise indicated herein or clearly contradicted by the context, the operations of the processes described herein may be performed in any suitable order. In at least one embodiment, processes such as those described herein (or variations thereof and / or combinations thereof) are executed under the control of one or more computer systems configured with executable instructions and are implemented as code (e.g., executable instructions, one or more computer programs, or one or more application programs) that is executed jointly on one or more processors via hardware or a combination thereof. In at least one embodiment, the code is stored on a computer-readable storage medium, for example, in the form of a computer program comprising a plurality of instructions executable by one or more processors. In at least one embodiment, the computer-readable storage medium is a non-transitory computer-readable storage medium that excludes transient signals (e.g., propagating transient electrical or electromagnetic transmissions) but includes non-transitory data storage circuitry (e.g., buffers, caches, and queues). In at least one embodiment, code (e.g., executable code or source code) is stored on one or more non-transitory computer-readable storage media (or other memory for storing executable instructions) on which executable instructions are stored, which, when executed by one or more processors of a computer system (in at least one embodiment, as a result of execution), cause the computer system to perform the operations described herein. In at least one embodiment, the set of non-transitory computer-readable storage media includes multiple non-transitory computer-readable storage media, and one or more of the individual non-transitory storage media lack all the code, but the multiple non-transitory computer-readable storage media collectively store all the code. In at least one embodiment, the executable instructions are executed such that different instructions are executed by different processors; for example, the non-transitory computer-readable storage media store the instructions, and the main central processing unit (“CPU”) executes some instructions while the graphics processing unit (“GPU”) executes others. In at least one embodiment, different components of the computer system have separate processors, and the different processors execute different subsets of the instructions.

[0082] Accordingly, in at least one embodiment, a computer system is configured to implement one or more services that individually or collectively perform the operations of the processes herein, and such a computer system is configured with suitable hardware and / or software to enable implementation of the operations. Moreover, a computer system implementing at least one embodiment of the present disclosure is a single device, and in another embodiment is a distributed computer system that includes multiple devices operating in different manners such that the distributed computer system performs the operations herein and such that a single device does not perform all of the operations.

[0083] The use of any and all examples, or exemplary language (e.g., "such as") provided herein is intended merely to better illuminate embodiments of the disclosure and does not pose a limitation on the scope of the disclosure unless otherwise claimed. No language in the specification should be construed as indicating any non-claimed element as essential to the practice of the disclosure.

[0084] All references, including publications, patent applications, and patents, cited herein are hereby incorporated by reference to the same extent as if each reference were individually and specifically indicated to be incorporated by reference and were set forth in its entirety herein.

[0085] In the description and claims, the terms "coupled" and "connected," along with derivatives thereof, can be used. It should be understood that these terms are not intended as synonyms for each other. Rather, in particular embodiments, "connected" or "coupled" is used to indicate that two or more elements are in direct or indirect physical or electrical contact with each other. "Coupled" can also mean that two or more elements are not in direct contact with each other, but yet still co-operate or interact with each other.

[0086] Unless specifically stated otherwise, it can be appreciated that throughout the specification, terms such as "processing," "computing," "calculating," "determining," or the like, refer to the action and / or processes of a computer or computing system, or similar electronic

[0087] In a similar manner, a “processor” can refer to any device or portion of a device that processes electronic data from registers and / or memory to transform that electronic data into other electronic data that can be stored in registers and / or memory. As a non-limiting example, a “processor” can be a CPU or GPU. A “computing platform” can include one or more processors. As used herein, a “software” process can include, for example, software and / or hardware entities such as tasks, threads, and intelligent agents that perform work over time. Likewise, each process can refer to multiple processes that execute instructions sequentially or in parallel, continuously or intermittently. The terms “system” and “method” can be used interchangeably herein so long as a system can embody a method or methods and a method can be considered a system.

[0088] In this document, references to obtaining, acquiring, receiving, or inputting analog or digital data into a subsystem, computer system, or computer-implemented machine can be made. Obtaining, acquiring, receiving, or inputting analog and digital data can be accomplished in a variety of ways, such as by receiving the data as a parameter of a function call or a call to an application programming interface. In some implementations, the process of obtaining, acquiring, receiving, or inputting analog or digital data can be accomplished by transmitting the data via a serial or parallel interface. In another implementation, the process of obtaining, acquiring, receiving, or inputting analog or digital data can be accomplished by transmitting the data from a providing entity to an acquiring entity via a computer network. Providing, outputting, transmitting, sending, or presenting analog or digital data can also be referenced. In various examples, the process of providing, outputting, transmitting, sending, or presenting analog or digital data can be accomplished by transmitting the data as an input or output parameter of a function call, a parameter of an application programming interface, or an interprocess communication mechanism.

[0089] Although the above discussion discusses example implementations of the described technology, other architectures can be used to implement the described functionality and are intended to be within the scope of the present disclosure. Moreover, although specific allocations of responsibilities have been defined above for purposes of discussion, various functions and responsibilities can be allocated and divided differently depending on the circumstances.

[0090] Moreover, although the subject matter has been described in language specific to structural features and / or methodological acts, it is to be understood that the subject matter defined in the appended claims is not necessarily limited to the specific features or acts described. Rather, the specific features and acts are disclosed as example forms of implementing the claims.

Claims

1. A cold plate for a data center liquid cooling system, comprising: a first portion, a second portion, and an intermediate layer, wherein the first portion and the second portion are hermetically and removably sealed together, and the intermediate layer is removably positioned within the first portion and the second portion; wherein the intermediate layer includes at least one first channel and a second channel for enabling coolant to flow from the at least one first channel through the second channel and out of a different first channel than the at least one first channel, the second channel for concentrating the coolant or coolant flow within the second channel, the second channel in the intermediate layer corresponding to at least a heat generating feature of an associated computing device, and the intermediate layer being replaceable by a second intermediate layer to address a second heat generated by a second component of a second associated computing device.

2. The cold plate of claim 1, further comprising: one or more gaskets associated with at least the first portion or the second portion to enable a hermetic seal when the first portion and the second portion are closed together.

3. The cold plate of claim 1, further comprising: a fluid adapter extending from the cold plate to enable receiving and flowing the coolant between the cold plate and at least a cooling manifold.

4. The cold plate of claim 1, wherein: the second intermediate layer includes at least a third channel and a fourth channel, and the second intermediate layer is used with the first portion and the second portion.

5. The cold plate of claim 1, further comprising: one or more first inlets in the intermediate layer corresponding to one or more second inlets of the first portion; and one or more first outlets in the intermediate layer corresponding to one or more second outlets of the first portion.

6. The cold plate of claim 1, further comprising: at least one slot traversing a length of the second channel, the slot having a surface area for concentrating the coolant or the coolant flow within the second channel.

7. The cold plate of claim 6, wherein: the at least one slot has at least one first dimension that is different from a dimension of the at least one first channel; and a second intermediate layer to be used in place of the intermediate layer, the second intermediate layer having at least one second slot with at least one second dimension that is different from the at least one first dimension and concentrates the coolant or the coolant flow into a second channel of the second intermediate layer.

8. The cold plate of claim 7, wherein: a wall of the at least one slot is perpendicular to a top surface and / or a bottom surface of the cold plate, the width of the at least one slot being the at least one first dimension; or a wall of the at least one slot is a circumferential structure, a diameter of the at least one slot being the at least one first dimension; or a wall of the at least one slot is at an angle relative to a top surface and / or a bottom surface of the cold plate, the angle of the at least one slot being the at least one first dimension. ​ ​ 9. A data center liquid cooling system comprising: A cold plate having a first portion, a second portion, and an intermediate layer, wherein the first portion and the second portion are hermetically and removably sealed together, and the intermediate layer is removably positioned within the first portion and the second portion; wherein the intermediate layer includes at least one first channel and a second channel for enabling a coolant to flow from the at least one first channel through the second channel and out of a different first channel than the at least one first channel, the second channel for concentrating the coolant or coolant flow within the second channel, the second channel positioned in the intermediate layer corresponding to at least a heat-generating component of an associated computing device, and the intermediate layer is replaceable by a second intermediate layer to address a second heat generated by a second component of a second associated computing device.

10. The data center liquid cooling system of claim 9, further comprising: a surface adaptation or material adaptation of the at least one second channel for enabling a first heat transfer of the coolant into the at least one second channel within the cold plate, the first heat transfer exceeding a second heat transfer of the coolant into a first channel.

11. The data center liquid cooling system of claim 9, further comprising: a fluid adapter for extending from the cold plate, the fluid adapter enabling receipt and outflow of the coolant between the cold plate and at least a cooling manifold of the data center liquid cooling system.

12. The data center liquid cooling system of claim 9, further comprising: one or more first inlets in the intermediate layer corresponding to one or more second inlets of the first portion; and one or more first outlets in the intermediate layer corresponding to one or more second outlets of the first portion.

13. The data center liquid cooling system of claim 9, further comprising: at least one slot in the intermediate layer of the cold plate, the slot traversing a length of the second channel to provide a surface area of the second channel for concentrating the coolant or the coolant flow.

14. The data center liquid cooling system of claim 13, further comprising: the at least one slot having at least one first dimension different from a dimension of the at least one first channel; and a second intermediate layer for replacing the intermediate layer, the second intermediate layer having at least one second slot with at least one second dimension different from the at least one first dimension and concentrating the coolant or the coolant flow into a second channel of the second intermediate layer.

15. The data center liquid cooling system of claim 14, wherein: a wall of the at least one slot is perpendicular with respect to a top surface and / or a bottom surface of the cold plate, a width of the at least one slot being the at least one first dimension; or a wall of the at least one slot is a circumferential structure, a diameter of the at least one slot being the at least one first dimension; or a wall of the at least one slot is a circumferential structure, a diameter of the at least one slot being the at least one first dimension; or The walls of the at least one slot are angled relative to a top surface and / or a bottom surface of the cold plate, the angle of the at least one slot being the at least one first dimension.

16. A method for a data center liquid cooling system, comprising: determining at least one computing component having a heat generating feature; providing a cold plate having a first portion and a second portion to be hermetically and removably sealed together; enabling a single intermediate layer of a plurality of intermediate layers to be removably located within the first portion and the second portion, wherein a first individual intermediate layer of the plurality of intermediate layers is replaceable with a second individual intermediate layer, the plurality of intermediate layers having respective first channels and respective second channels to enable coolant to flow from at least one first channel through a second channel and out of a different first channel than the at least one first channel, the respective second channels to concentrate the coolant or a flow of coolant within the respective second channels to correspond to the heat generating feature.

17. The method of claim 16, further comprising: determining a region of the cold plate associated with the heat generating feature; and determining that the first individual intermediate layer has a second channel to concentrate the coolant or the flow of coolant to a region within the cold plate by exposing more heat transfer surface area to the coolant than the first channel.

18. The method of claim 16, further comprising: associating the cold plate with the at least one computing component; and associating an inlet coolant line with an inlet of the first portion and an outlet coolant line with an outlet of the first portion.

19. The method of claim 16, further comprising: determining a second computing component to replace the at least one computing component, the second computing component having a second heat generating feature; determining a second region within the cold plate associated with the second heat generating feature; and determining that the second individual intermediate layer has a second channel to concentrate the coolant or the flow of coolant to the second region within the cold plate.

20. A method for manufacturing a configurable cold plate, comprising: providing a first portion having at least one inlet and at least one outlet for coupling to a fluid adapter of a cooling loop; providing a second portion for hermetically and removably sealing with the first portion; and machining a single intermediate layer of a plurality of intermediate layers to be removably located within the second portion and the first portion, respective intermediate layers of the plurality of intermediate layers having respective first channels and respective second channels to enable coolant to flow from at least one first channel through a second channel and out of a different first channel than the at least one first channel, the respective second channels to concentrate the coolant or a flow of coolant within the respective second channels.

21. The method of claim 20, further comprising: providing one or more gaskets to enable the hermetic and removable sealing between the first portion and the second portion.

22. The method of claim 20, further comprising: ​ One or more latching clips are provided for achieving the air-tight and removable seal between the first portion and the second portion.

23. The method of claim 20, further comprising: determining cooling requirements of at least one computing component; drilling first channels in one or more intermediate layers for enabling a flow of the coolant to flow therein; and drilling second channels for concentrating the coolant or the flow of the coolant within the second channels according to locations of the cooling requirements of the at least one computing component.

24. The method of claim 20, further comprising: determining cooling requirements of at least one computing component; and printing or growing one or more intermediate layers to include first channels and to include second channels according to locations of the cooling requirements of the at least one computing component.

Images