Component cooler for computing device
By using multiple heat pipes and thermoelectric coolers in computing devices, the heat of the components is split and dispersed, and the cooling is accelerated by using a fluid manifold, the problem of difficulty in effectively removing heat from high-power components in the prior art is solved, and more efficient cooling and performance improvements are achieved.
Patent Information
- Application Number
- CN202380069708.X
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Priority Date
- 2022-09-29
- Filing Date
- 2023-09-08
- Publication Date
- 2025-05-13
AI Technical Summary
Existing computing device cooling solutions are difficult to effectively remove heat under high power consumption and high density of components such as processors, making it difficult to control the temperature and affect performance.
The heat load generated by the assembly is split by multiple conduction paths between the plurality of heat transfer elements and accelerates the dissipation of heat through the fluid flow path across the plurality of surfaces. At the same time, a thermoelectric cooler is used to provide cooling at sub-ambient temperature to enhance cooling efficiency.
Through the combination of multiple heat transfer paths and fluid manifolds, more efficient and efficient cooling of components within the computing device is achieved, thereby more efficiently removing heat from components, reducing temperature and improving performance.
Smart Images

Figure CN119998758A_ABST
Abstract
Description
Background Art
[0001] Computing devices include various components, including processors and graphics processing units (GPUs), which generate heat. To dissipate the heat generated by these components, computing devices typically include one or more cooling elements. Such cooling elements include, for example, fluid cooling systems, heat pipes, vapor chambers, radiators, fans, and the like. BRIEF DESCRIPTION OF THE DRAWINGS
[0002] Figure 1 is a diagram of a non-limiting exemplary component cooling arrangement according to some implementations of the present disclosure.
[0003] Figure 2 According to the specific implementation of this disclosure Figure 1 Side view of the component cooling device.
[0004] Figure 3 According to the specific implementation of this disclosure Figure 1 A perspective view of a portion of a component cooling device.
[0005] Figure 4 According to the specific implementation of this disclosure Figure 3 Exploded view of a portion of the component cooling arrangement.
[0006] Figure 5 According to the specific implementation of this disclosure Figure 3 Another exploded view of a portion of the assembly cooling arrangement.
[0007] Figure 6 is a specific implementation of a fluid manifold according to a specific implementation of the present disclosure.
[0008] Figure 7 is a specific implementation of a heat pipe assembly according to a specific implementation of the present disclosure.
[0009] Figure 8 is another implementation of a heat pipe assembly according to an implementation of the present disclosure.
[0010] Figure 9 is another implementation of a heat pipe assembly according to an implementation of the present disclosure.
[0011] Figure 10 is another exemplary component cooling device according to some implementations of the present disclosure.
[0012] Figure 11 is another exemplary component cooling device according to some implementations of the present disclosure.
[0013] Figure 12 is a block diagram of an exemplary computing device for component cooling, according to some implementations.
[0014] Figure 13 A flowchart illustrating an exemplary method for component cooling according to some implementations is listed. DETAILED DESCRIPTION
[0015] As the demand for greater processing power increases, dissipating heat from integrated circuits (ICs) such as central processing units (CPUs), accelerated processing units (APUs), graphics processing units (GPUs), application-specific ICs (ASICs), and field-programmable gate arrays (FPGAs) becomes more difficult. There is a constant push to increase power consumption and power density in ICs. For example, in processors, higher power consumption generally correlates with higher performance. Furthermore, as processor technology advances, the number and density of transistors in a processor generally increase, resulting in faster and more energy-efficient processors. As transistor density increases, heat is more concentrated in one area, making it more difficult to remove heat from the processor. Similar advances have been made in other types of ICs, resulting in similar concentration and increased heat generation.
[0016] Thermal cooling solutions are often used to help remove heat from components (such as ICs) of computing devices. Maintaining lower IC temperatures can equate to higher performance. Thermal solutions (such as coolers) that dissipate heat more efficiently typically result in lower IC temperatures. Computing devices typically include one or more cooling elements for dissipating heat generated by various ICs, such as processor cores. Such cooling elements include, for example, radiators, fluid cooling systems (e.g., water cooling systems), vapor chambers, heat pipes, fans, etc., to conduct heat generated by the ICs of the computing device to fans that dissipate the heat out of the computing device. However, existing solutions may not be sufficient to cool the components of a computing system due to the use of ambient temperature air for cooling and / or the lack of sufficient thermal contact between the heat-generating components and the heat-dissipating components.
[0017] This specification lists a component cooler for a computing device. In one or more specific implementations, the component cooler utilizes multiple heat pipes to split the heat load generated by the component through multiple conduction paths between multiple heat transfer elements to facilitate removing heat from the component. The component cooler includes multiple fluid flow paths across multiple surfaces to facilitate removing heat from the component. The component cooler may also include one or more thermoelectric coolers (TECs) in contact with one or more of the heat transfer elements to provide sub-ambient temperature cooling to the heat transfer elements and facilitate removing heat from the component. Therefore, by utilizing multiple heat transfer paths and a manifold having multiple fluid flow paths, more effective and efficient cooling of components within the computing device is provided, thereby more effectively removing heat from the components of the computing device.
[0018] In some implementations, a device for component cooling is provided, the device comprising a first heat transfer element configured to be thermally coupled to a heat-generating electronic component; a second heat transfer element; and a plurality of heat transfer paths thermally coupled between the first heat transfer element and the second heat transfer element. Each of the plurality of heat transfer paths is configured to provide a separate heat conduction path from the first heat transfer element to the second heat transfer element. The device also comprises a manifold comprising a first fluid channel providing a first portion of a heat transfer fluid in thermal contact with the first heat transfer element, and a second fluid channel providing a second portion of the heat transfer fluid in thermal contact with the second heat transfer element.
[0019] In some implementations, wherein the heat-generating electronic component comprises a processor, in some implementations, the plurality of heat transfer paths comprises at least one heat pipe, in some implementations, the plurality of heat transfer paths comprises at least one vapor chamber.
[0020] In some implementations, the first heat transfer element includes at least one of a first substrate and a second substrate. In some implementations, a portion of the plurality of heat transfer paths is disposed between the first substrate and the second substrate. In some implementations, the apparatus further includes a first thermoelectric cooler thermally coupled to the first heat transfer element. In some implementations, the apparatus further includes a first cold plate, wherein the first thermoelectric cooler is configured to transfer heat from the first heat transfer element to the first cold plate. In some implementations, the first fluid channel passes through the first cold plate.
[0021] In some implementations, the second heat transfer element includes at least one of a third substrate and a fourth substrate. In some implementations, a portion of the plurality of heat transfer paths is disposed between the third substrate and the fourth substrate.
[0022] In some implementations, the apparatus further comprises a second thermoelectric cooler thermally coupled to the second heat transfer element. In some implementations, the apparatus further comprises a second cold plate, wherein the second thermoelectric cooler is configured to transfer heat from the second heat transfer element to the second cold plate. In some implementations, the second fluid channel passes through the second cold plate.
[0023] In some implementations, a device for component cooling is provided, the device comprising a first heat transfer element configured to be thermally coupled to a heat-generating electronic component; a second heat transfer element; and a plurality of heat transfer paths thermally coupled between the first heat transfer element and the second heat transfer element. Each of the plurality of heat transfer paths is configured to provide a separate thermally conductive path from the first heat transfer element to the second heat transfer element. The device also comprises a cooling block comprising a channel for providing a heat transfer fluid in thermal contact with the first heat transfer element.
[0024] In some implementations, the apparatus further comprises a cooling fan assembly coupled to the second heat transfer element. In some implementations, the heat-generating electronic component comprises a processor. In some implementations, the plurality of heat transfer paths comprises at least one heat pipe. In some implementations, the first heat transfer element comprises at least one of a first substrate and a second substrate. In some implementations, the second heat transfer element comprises a cold plate.
[0025] References Figure 1 The initial figures depict various implementations of component cooling arrangements. Figure 1 is a diagram of a non-limiting exemplary component cooling arrangement 100 according to some implementations of the present disclosure. Figure 1 The exemplary component cooling arrangement 100 is shown in a cross-sectional view. The exemplary component cooling arrangement 100 can be implemented in various computing devices, including desktop computing devices, mobile computing devices, laptop computers, tablet computers, hybrid laptop / tablet computing devices, gaming devices, set-top boxes, and the like.
[0026] Figure 1 The exemplary component cooling device 100 includes a base plate 102 . Figure 1 The substrate 102 can be a printed circuit board (PCB), such as a motherboard of a computing device. The substrate 102 is coupled to an IC socket 104, which is further coupled to the bottom surface of a processor 106. A processor is used here as an example of a heat-generating component, but readers familiar with the art will recognize that components that can benefit from the exemplary cooling arrangements described herein can include any type of IC. In various examples, the processor 106 includes a CPU, an APU, a GPU, an FPGA, an ASIC, or a digital signal processor (DSP).
[0027] The top surface of processor 106 is thermally coupled to the bottom surface of first substrate 108A. The substrate is a component of the heat pipe assembly through which the various heat pipes conduct heat. First substrate 108A is connected to base plate 102 via mounting plate 107. The top surface of first substrate 108A is coupled to the bottom surface of second substrate 108B. First substrate 108A and second substrate 108B can be made of a conductive metal such as copper. In some implementations, first substrate 108A and second substrate 108B are replaced with a single substrate.
[0028] The top surface of the second substrate 108B is thermally coupled to the bottom surface of a first thermoelectric cooler (TEC) 110A. A TEC is a semiconductor device with two sides that act to transfer heat from one side to the other when current passes through the TEC. The top surface of the first TEC 110A is thermally coupled to a first cold plate 112A. A cold plate is a device that uses a fluid to transfer heat from the device to a remote heat exchanger. Although various embodiments are described using a cold plate as a heat transfer element, in other embodiments, other suitable heat transfer elements are used, such as a substrate or a heat sink.
[0029] Component cooling device 100 also includes a second cold plate 112B having a top surface thermally coupled to the bottom surface of second TEC 110B. The top surface of second TEC 110B is thermally coupled to the bottom surface of third substrate 108C. The top surface of third substrate 108C is coupled to the bottom surface of fourth substrate 108D. Third substrate 108C and fourth substrate 108D are composed of a conductive metal such as copper. In certain implementations, third substrate 108C and fourth substrate 108D are replaced with a single substrate.
[0030] Figure 1 The component cooling arrangement further includes a third cold plate 112C having a bottom surface thermally coupled to the top surface of the fourth base plate 108D. In a specific implementation, each of the first cold plate 112A, the second cold plate 112B, and the third cold plate 112C includes a plurality of fins to facilitate heat transfer to a heat transfer medium, such as air or a fluid.
[0031] The component cooling device 100 also includes a plurality of heat pipes 114A, 114B, 114C, and 114D. Each of the heat pipes 114A-114D has a first end disposed between and in thermal contact with the first substrate 108A and the second substrate 108B, and a second end disposed between and in thermal contact with the third substrate 108C and the fourth substrate 108D. Each of the heat pipes 114A, 114B, 114C, and 114D includes a middle portion between the first end and the second end, the middle portion being external to each of the substrates 108A, 108B, 108C, and 108D. In one or more specific implementations, each of the heat pipes 114A, 114B, 114C, and 114D forms a semi-ring configuration, such as Figure 2 As further shown in Figure 1In the illustrated implementation, heat pipes 114A-114D have a substantially circular cross-section. In a particular implementation, heat pipes 114A and 114C extend from one side of component cooling device 100, and heat pipes 114B and 114D extend from the opposite side of component cooling device 100. Although various implementations are described as using heat pipes as heat transfer structures, other implementations may utilize other suitable heat transfer structures, such as, for example, a vapor chamber.
[0032] Component cooling device 100 also includes a fluid manifold. The fluid manifold includes a manifold inlet portion 116A and a manifold outlet portion 116B, disposed on opposite sides of component cooling device 100. Manifold inlet portion 116A includes a fluid inlet 118A, and manifold outlet portion 116B includes a fluid outlet 118B. In certain implementations, fluid inlet 118A and fluid outlet 118B are positioned in opposite directions. In other implementations, fluid inlet 118A and fluid outlet 118B are positioned in the same direction or in any direction.
[0033] The fluid manifold includes a first fluid channel 120A extending from manifold inlet portion 116A to manifold outlet portion 116B. First fluid channel 120A is in thermal contact with first cold plate 112A. The fluid manifold includes a second fluid channel 120B extending from manifold inlet portion 116A to manifold outlet portion 116B and in thermal contact with second cold plate 112B. The fluid manifold also includes a third fluid channel 120C extending from manifold inlet portion 116A to manifold outlet portion 116B and in thermal contact with third cold plate 112C. During operation of component cooling device 100, a fluid circuit including a fluid pump and a heat sink (not shown) is coupled between fluid inlet 118A and fluid outlet 118B via piping or the like. The fluid pump causes cooling fluid within the fluid manifold to flow into manifold inlet portion 116A. The cooling fluid is split through each of first fluid channel 120A, second fluid channel 120B, and third fluid channel 120C. The separated flows are combined in manifold outlet portion 116B and output to a radiator from fluid outlet 118B.
[0034] In a specific implementation, the fluid flow rate through each of the first fluid channel 120A, the second fluid channel 120B, and the third fluid channel 120C is varied by configuring one or more of the first fluid channel 120A, the second fluid channel 120B, and the third fluid channel 120C to be different in size from one another to achieve a desired flow rate through each of the fluid channels 120A, 120B, and 120C. In a specific example, the first fluid channel 120A is sized to have a greater flow rate than the second fluid channel 120B and the third fluid channel 120C because the amount of heat expected to be transferred to the first fluid channel 120A is greater than the amount of heat expected to be transferred to the second fluid channel 120B and the third fluid channel 120C. In a specific implementation, the diameter of the first fluid channel 120A is greater than the diameter of the second fluid channel 120B or the third fluid channel 120C. In another embodiment, one or more controllable valves are positioned within one or more of the first fluid passage 120A, the second fluid passage 120B, and the third fluid passage 120C to allow for varying flow rates through the fluid passages. Figure 1 The illustrated implementation includes three fluid channels, but other implementations have fewer than three or more than three fluid channels within the fluid manifold.
[0035] The component cooling device 100 includes a first spring mechanism 122A and a second spring mechanism 122B. The first spring mechanism 122A is disposed between the manifold inlet portion 116A and the third cold plate 112C. The first spring mechanism 122A is rigidly coupled to the sidewall of the manifold inlet portion 116A and applies a first upward force to the manifold inlet portion 116A and a first downward force to the third cold plate 112C. The terms "upward" and "downward" are used herein for ease of explanation only and are relative to Figure 1 For the example shown. The second spring mechanism 122B is disposed between the manifold outlet portion 116B and the third cold plate 112C. The second spring mechanism 122B is rigidly coupled to the sidewall of the manifold outlet portion 116B and applies a second upward force to the manifold outlet portion 116B and a second downward force to the third cold plate 112C. The forces applied to the third cold plate 112C by the first spring mechanism and the second spring mechanism cause the third cold plate to maintain thermal contact with the fourth base plate 108D. Figure 1 In a specific implementation, a first spring mechanism and a second spring mechanism are positioned on opposite ends of the third cold plate 112C and press the third cold plate toward the fourth cold plate 108D. At the opposite ends, the forces applied by the two springs to the third cold plate are effectively balanced, causing the third cold plate to press against (and thermally couple to) the fourth cold plate with a relatively equal distribution over the surface areas of the third and fourth cold plates.
[0036] Figure 1The component cooling device 100 further includes a third spring mechanism 122C and a fourth spring mechanism 122D disposed between the second cold plate 112B and the first cold plate 112A. The third spring mechanism 122C and the fourth spring mechanism 122D are configured to apply a force between the first cold plate 112A and the second cold plate 112B to maintain thermal contact between the first cold plate 112A and the first TEC 110A, and to maintain thermal contact between the second cold plate 112B and the second TEC 110B.
[0037] Each of the first spring mechanism 122A, the second spring mechanism 122B, the third spring mechanism 122C, and the fourth spring mechanism 122D is coupled to a side portion of the fluid manifold. Figure 1 In the illustrated implementation, the first and third spring mechanisms 122A, 122C are coupled to one side of the manifold inlet portion 116A, and the second and fourth spring mechanisms 122B, 122D are coupled to one side of the manifold outlet portion 116B. In various implementations, the spring mechanisms 122A-122D include, for example, one or more of leaf springs, coil springs, pneumatic (e.g., gas and / or fluid) springs, or flat springs.
[0038] The third spring mechanism 122C is rigidly coupled to the sidewalls of the manifold inlet portion 116A and applies an upward force to the second cold plate 112B and a downward force to the first cold plate 112A. Similarly, the fourth spring mechanism 122D is rigidly coupled to the sidewalls of the manifold outlet portion 116B and applies an upward force to the second cold plate 112B and a downward force to the first cold plate 112A. Thus, thermal contact is maintained between the first cold plate 112A and the first TEC 110A, and between the second cold plate 112B and the second TEC 110B.
[0039] Typical thermal solutions that utilize a spring mechanism to maintain thermal contact between surfaces do not rigidly attach the spring mechanism to the surface. Therefore, maintaining the position of the spring mechanism during assembly of the component cooler is more difficult. Furthermore, when the spring mechanism is not rigidly attached to the surface, the spring mechanism is more likely to become dislodged during use of the component cooler. Figure 1In the component cooler 100, the rigid coupling of the first spring mechanism 122A, the second spring mechanism 122B, the third spring mechanism 122C, and the fourth spring mechanism 122D to the fluid manifold facilitates easier assembly of the component cooler arrangement 100. In an exemplary implementation, the first spring mechanism 122A, the second spring mechanism 122B, the third spring mechanism 122C, and the fourth spring mechanism 122D are rigidly attached to the fluid manifold prior to installing the cold plates 112A-112C, such that the positions of the spring mechanisms are maintained during assembly. Furthermore, the rigid coupling of the spring mechanisms to the fluid manifold helps maintain the positions of the spring mechanisms during use of the component cooler arrangement 100.
[0040] In this example, the spring mechanisms all have substantially the same width and spring constant, resulting in substantially the same distance between the two objects to which the spring mechanisms exert force. The spring constant defines the ratio of the force acting on a spring to the displacement caused by the spring. When two springs have the same spring constant and width, they will exert substantially the same force on two objects of similar mass, creating the same distance between them. For example, the first spring mechanism 122A has a substantially similar width and spring constant as the third spring mechanism 122C. Thus, the distance between the manifold inlet portion 116A and the third cold plate 112C (maintained by the force of the first spring mechanism) is substantially equal to the distance between the second cold plate 112B and the first cold plate 112A (maintained by the force of the second spring mechanism). The width and spring constant of the spring mechanisms can be selected so that, when the spring mechanisms are compressed, the distances between the cold plates and between the manifold portion and the cold plate can provide gaps of varying sizes, depending on the desired thermal properties. For example, larger gaps provide additional airflow across surfaces (such as the cold plate surface), which in some cases results in additional cooling due to greater heat dissipation relative to smaller gaps. In other cases, a smaller gap between two components (such as two cold plates) can result in additional cooling efficiency of the components.
[0041] Figure 1The exemplary component cooling device 100 provides multiple heat conduction paths between heat transfer elements for removing heat generated by the processor 106, as further described below. During operation of the processor 106, heat generated by the processor is transferred to a first substrate 108A thermally coupled to the processor 106, and a portion of the heat transferred to the first substrate 108A is further transferred to the second substrate 108B. Each of the heat pipes 114A, 114B, 114C, and 114D is configured to transfer a portion of the heat received from the first and second substrates 108A, 108B to the third and fourth substrates 108C, 108D. In certain implementations, the heat pipes 114A, 114B, 114C, and 114D utilize phase changes between heat transfer fluids within the heat pipes 114A, 114B, 114C, and 114D to transfer heat from the first and second substrates 108A, 108B to the third and fourth substrates 108C, 108D.
[0042] The first TEC 110A is controlled to remove a certain amount of heat from the second substrate 108B and transfer the heat to the first cold plate 112A. In one embodiment, the amount of heat transferred by the first TEC 110A is controlled by adjusting the current supplied to the first TEC 110A. The first TEC 110A provides sub-ambient cooling to the second substrate 108B. The second TEC 110B is controlled to remove a certain amount of heat from the third substrate 108C and transfer the heat to the second cold plate 112B. The amount of heat transferred by the second TEC 110B is controlled by adjusting the current supplied to the second TEC 110B. The second TEC 110B provides sub-ambient cooling to the third substrate 108C. In one or more embodiments, the amount of power supplied to one or more of the first TEC 110A or the second TEC 110B is adjusted based on monitored system parameters, such as processor activity, to control the amount of cooling provided by the respective TEC.
[0043] A fluid pump (not shown) causes a cooling fluid flow to enter manifold inlet portion 116A through fluid inlet 118A. The fluid is split to flow through each of first fluid channel 120A, second fluid channel 120B, and third fluid channel 120C. First fluid channel 120A is in thermal contact with first cold plate 112A, second fluid channel 120B is in thermal contact with second cold plate 112B, and third fluid channel 120C is in thermal contact with third cold plate 112C. When the fluid flows through first fluid channel 120A, a portion of heat is transferred from first cold plate 112A to the fluid. Similarly, when the fluid flows through second fluid channel 120B, a portion of heat is transferred from second cold plate 112B to the fluid. When the fluid flows through third fluid channel 120C, a portion of heat is transferred from third cold plate 112C to the fluid. The separate flows from each of the first fluid channel 120A, the second fluid channel 120B, and the third fluid channel 120C are combined within the manifold outlet portion 116B and output from the fluid outlet 118B to one or more heat sinks (not shown).
[0044] To explain further, Figure 2 Shows a specific implementation according to the present disclosure Figure 1 1. A side view of a component cooling device 100. Figure 2 Heat pipes 114A, 114B, 114C, and 114D are shown in a ring configuration. A first end of each of the heat pipes 114A, 114B, 114C, and 114D is in thermal contact with the first and second substrates 108A, 108B. A second end of each of the heat pipes 114B, 114C, and 114D is in thermal contact with the third and fourth substrates 108C, 108D.
[0045] To explain further, Figure 3 Shows a specific implementation according to the present disclosure Figure 1 A perspective view of a portion of an assembly cooling device 100 . Figure 3 Component cooling is shown decoupled from the processor 106 and base plate 102 .
[0046] To explain further, Figure 4 Shows a specific implementation according to the present disclosure Figure 3 Exploded view of a portion of the component cooling arrangement. Figure 4 The manifold inlet portion 116A and the manifold outlet portion 116B are shown disconnected from the first cold plate 112A, the second cold plate 112B, and the third cold plate 112C. Figure 4 Also shown are the first cold plate 112A, the second cold plate 112B, and the third cold plate 112C disconnected from the heat pipe assembly 402. The heat pipe assembly includes Figure 1 Heat pipes 114A-114D and substrates 108A-108D are shown. Figure 4Also shown are a first fluid channel 120A through the first cold plate 112A, a second fluid channel 120B through the second cold plate 112B, and a third fluid channel 120C through the third cold plate 112C.
[0047] To explain further, Figure 5 Shows a specific implementation according to the present disclosure Figure 3 Another exploded view of a portion of the assembly cooling arrangement. Figure 5 The manifold inlet portion 116A and the manifold outlet portion 116B are shown disconnected from the first cold plate 112A, the second cold plate 112B, and the third cold plate 112C. Figure 5 Also shown are the first cold plate 112A, the second cold plate 112B, and the third cold plate 112C coupled to the heat pipe assembly 402 .
[0048] To explain further, Figure 6 Another implementation of a fluid manifold 600 according to an implementation of the present disclosure is shown. Figure 6 A cross-sectional view of a fluid manifold 600 is shown that includes a manifold inlet portion 602A and a manifold outlet portion 602B. The manifold inlet portion 602A includes a fluid inlet 604A, and the manifold outlet portion 602B includes a fluid outlet 604B. In a specific implementation, the fluid inlet 604A and the fluid outlet 604B are each positioned in the same direction. In other specific implementations, the fluid inlet 604A and the fluid outlet 604B are each positioned in any desired direction. The fluid manifold includes a first fluid channel 606A connecting the manifold inlet portion 602A to the manifold outlet portion 116B and in thermal contact with the first cold plate 112A. The fluid manifold includes a second fluid channel 606B connecting the manifold inlet portion 602A to the manifold outlet portion 602B and in thermal contact with the second cold plate 112B. The fluid manifold also includes a third fluid channel 606C connecting the manifold inlet portion 602A to the manifold outlet portion 602B and in thermal contact with the third cold plate 112C. Figure 6 In the illustrated implementation, the manifold inlet portion 602A and the manifold outlet portion 602B are positioned behind, and not in direct contact with, the first, second, and third cold plates 112A, 112B, 112C.
[0049] To explain further, Figure 7 Another embodiment of a heat pipe assembly 700 according to an embodiment of the present disclosure is shown. The heat pipe assembly 700 includes a first heat pipe 702A, a second heat pipe 702B, a third heat pipe 702C, a fourth heat pipe 702D, a first base plate 108A, a second base plate 108B, a third base plate 108C, and a fourth base plate 108D. Figure 7In the illustrated implementation, heat pipes 702A-702D have a substantially rectangular cross-section. Each of heat pipes 702A-702D includes a first end in thermal contact with the first substrate 108A and the second substrate 108B, and a second end in thermal contact with the third substrate 108C and the fourth substrate 108D. Although various implementations illustrate heat pipes having substantially circular cross-sections and substantially rectangular cross-sections, other implementations include heat pipes having any suitable cross-section.
[0050] To explain further, Figure 8 FIG. 8 is another embodiment of a heat pipe assembly 800 according to an embodiment of the present disclosure. The heat pipe assembly 800 includes a first heat pipe 114A, a second heat pipe 114B, a third heat pipe 114C, a fourth heat pipe 114D, a first base plate 108A, a second base plate 108B, a third base plate 108C, and a fourth base plate 108D. Figure 8 In the illustrated implementation, the heat pipes 114A-114D have a substantially circular cross-section. Each of the heat pipes 114A-114D includes a first end in thermal contact with the first and second substrates 108A and 108B, and a second end in thermal contact with the third and fourth substrates 108C and 108D.
[0051] To explain further, Figure 9 Another embodiment of a heat pipe assembly 900 according to an embodiment of the present disclosure is shown. The heat pipe assembly 900 includes a first heat pipe 902A, a second heat pipe 902B, a third heat pipe 902C, a fourth heat pipe 902D, a first base plate 904A, a second base plate 904B, and a third base plate 904C. Figure 8 In the illustrated embodiment, heat pipes 902A-902D have a substantially circular cross-section. In one embodiment, third substrate 904C has a larger surface area than first substrate 904A and second substrate 904B. Each of heat pipes 902A-902D includes a first end in thermal contact with first substrate 904A and second substrate 904B, and a second end in thermal contact with third substrate 904C.
[0052] To explain further, Figure 10 Another exemplary component cooling device 1000 according to some implementations of the present disclosure is shown. Figure 10 As shown, the component cooling device 1000 includes Figure 6 The fluid manifold 600 shown is Figure 7 The heat pipe assembly 700 is coupled.
[0053] To explain further, Figure 11 Another example component cooling arrangement 1100 is shown according to some implementations of the present disclosure. Figure 11The exemplary component cooling device 1100 includes a substrate 1102 coupled to an IC socket 1104, which is further coupled to a processor 1106. Substrate 1102 includes, for example, a PCB, such as a motherboard of a computing device. In various examples, processor 1106 includes one or more of a CPU, an APU, a GPU, an FPGA, an ASIC, or a DSP. The top surface of processor 1106 is thermally coupled to the bottom surface of a first substrate 1108A. In specific implementations, first substrate 1108A is connected to substrate 1102 via one or more standoffs. The top surface of first substrate 1108A is coupled to the bottom surface of second substrate 1108B. In one or more specific implementations, first substrate 1108A and second substrate 1108B are comprised of a conductive metal, such as copper. In specific implementations, first substrate 1108A and second substrate 1108B are replaced with a single substrate.
[0054] The top surface of second base plate 1108B is thermally coupled to the bottom surface of fluid block 1110. Fluid block 1110 includes a fluid inlet 1112A and a fluid outlet 1112B. Fluid block 1110 includes a fluid channel extending from fluid inlet 1112A to fluid outlet 1112B and in thermal contact with second base plate 1108B. During operation of component cooling device 1100, a fluid circuit including a fluid pump and a heat sink (not shown) is coupled between fluid inlet 1112A and fluid outlet 1112B via piping or the like. The fluid pump causes a heat transfer medium (such as water) within fluid block 1110 to flow from fluid inlet 1112A to fluid outlet 1112B, thereby facilitating the removal of heat from second base plate 1108B to the heat sink.
[0055] The component cooling device 1100 also includes a heat sink fin stack 1114 having a top surface coupled to a bottom surface of a cooling fan assembly 1116 that is configured to direct airflow toward the heat sink fin stack 1114. In a particular implementation, the heat sink fin stack 1114 includes a plurality of fins to facilitate removal of heat from the heat sink fin stack 1114 via airflow. The heat sink fin stack 1114 is supported by the base plate 1102 via a support frame 1118. In a particular implementation, the heat sink fin stack 1114 is substantially larger than either the first base plate 1108A or the second base plate 1108B.
[0056] Component cooling device 1100 further includes a plurality of heat pipes 1120A, 1120B, 1120C, and 1120D. Each of heat pipes 1120A, 1120B, 1120C, and 1120D has a first end disposed between and in thermal contact with first base plate 1108A and second base plate 1108B, and a second end in thermal contact with heat sink fin stack 1114. Each of heat pipes 1120A, 1120B, 1120C, and 1120D includes an intermediate portion between the first and second ends, the intermediate portion being external to each of base plates 1108A, 1108B, and heat sink fin stack 1114.
[0057] In one or more specific implementations, each of the heat pipes 1120A, 1120B, 1120C, and 1120D is formed in a half-ring configuration. Figure 11 In the illustrated implementation, heat pipes 1120A-1120D have a substantially circular cross-section. In a particular implementation, heat pipes 1120A and 1120B extend from one side of component cooling device 1100, and heat pipes 1120C and 1120D extend from the opposite side of component cooling device 1100. Although various implementations are described as using heat pipes as heat transfer structures, other implementations utilize other suitable heat transfer structures, such as vapor chambers.
[0058] Figure 11 The exemplary component cooling device 1100 provides multiple thermally conductive paths between heat transfer elements for removing heat generated by the processor 1106, as further described below. During operation of the processor 1106, heat generated by the processor 1106 is transferred to a first base plate 1108A thermally coupled to the processor 1106, and a portion of the heat transferred to the first base plate 1108A is transferred to the second base plate 1108B. Each of the heat pipes 1120A, 1120B, 1120C, and 1120D is configured to transfer a portion of the heat received from the first base plate 1108A and the second base plate 1108B to the heat sink fin stack 1114. The heat pipes 1120A, 1120B, 1120C, and 1120D utilize phase changes between the heat transfer fluid within the heat pipes 1120A, 1120B, 1120C, and 1120D to transfer heat from the first base plate 1108A and the second base plate 1108B to the heat sink fin stack 1114.
[0059] In another implementation, the component cooling device 1100 further includes a TEC positioned between and in thermal contact with the second base plate 1108B and the fluid block 1110. In another implementation, the component cooling device 1100 further includes a TEC positioned between and in thermal contact with the heat sink fin stack 1114 and the cooling fan assembly 1116.
[0060] Figure 12 1 is a block diagram of an exemplary computing device 1200 for a component cooling arrangement according to some implementations. Computing device 1200 includes an APU 1202. APU 1202 is a microprocessor that includes a CPU 1204 and an integrated graphics processing unit (iGPU) 1207 on a single die. Computing device 1200 also includes a discrete graphics processing unit (dGPU) 1208. Although the methods described herein are described in the context of computing device 1200 including a dGPU 1208 and an APU 1202 with an iGPU 1207, it should be understood that the methods described herein are applicable to any system or device that incorporates both integrated and discrete GPUs. The dGPU 1208 is a peripheral or add-on component of computing device 1200 that is operatively coupled to APU 1202. For example, in some implementations, dGPU 1208 is operatively coupled to APU 1202 via a Peripheral Component Interface Express (PCIe) bus. Thus, in such implementations, the dGPU 1208 is installed in a PCIe port on a motherboard or other PCB in which the APU 1202 is installed. With the operable connection between the APU 1202 and the dGPU 1208, the APU 1202 can issue instructions, render jobs, etc. to the dGPU 1208. In some implementations, the dGPU 1208 includes a display interface 1210. The display interface 1210 is a port or socket to which an external monitor or display is connected. The display interface 1210 provides a video signal to the external display for presentation. The display interface 1210 includes, for example, a High-Definition Multimedia Interface (HDMI) port, a Video Graphics Array (VGA) port, a Digital Video Interface (DVI) port, a Universal Serial Bus-C (USB-C) port, or other display ports as will be appreciated.
[0061] The iGPU 1207 and the dGPU 1208 each include one or more video cores 1212. A video core 1212 is a discrete processing unit, core, or other unit of hardware resources dedicated to encoding and decoding video data. For example, each video core 1212 facilitates video encoding or decoding operations, such as decoding streaming video content, encoding video for video conferencing applications, encoding video files for later playback, etc. In some implementations, the video cores 1212 implement a specific hardware architecture or configuration for video encoding and decoding, such as Video Core Next (VCN).
[0062] iGPU 1207 and dGPU 1208 also each include one or more compute units 1214. Each compute unit 1214 includes one or more cores that share a local cache, thereby allowing parallel processing and cache access to each core within a given compute unit 1214. Compute units 1214 facilitate various computational and processing jobs submitted to iGPU 1207 and dGPU 1208, including rendering operations, machine learning operations, and the like.
[0063] The iGPU 1207 and dGPU 1208 also each include a display engine 1216. Each display engine 1216 manages the presentation of video or image content to a display of the computing device 1200 (e.g., an internal mobile device display or an external display coupled to the display interface 1210). In some implementations, the display engine 1216 implements display core technologies such as Display Core Next (DCN). The APU 1202 also includes an audio coprocessor (ACP) 1206. The ACP 1206 is a core, processor, or other allocation of hardware components dedicated to audio encoding and decoding.
[0064] The computing device 1200 also includes a memory 1220 , such as random access memory (RAM). Stored in the memory 1220 are an operating system 1222 and a voltage configuration module 1224 . Figure 12 The operating system 1222 and voltage configuration module 1224 in the example of are shown as being located in the memory 1220, but many components of such software are also typically stored in non-volatile memory, such as, for example, on a disk drive or other storage medium. According to some specific implementations, operating systems 1222 useful in the computing device 1200 include: UNIX TM 、Linux TM , Microsoft Windows TM and other operating systems apparent to those skilled in the art.
[0065] The voltage configuration module 1224 is a module for controlling the voltages allocated to the APU 1202 and dGPU 1208. For example, the voltage configuration module 1224 implements SmartShift technology for allocating voltages to enhance performance for specific applications. Depending on the specific workload being executed on the computing device 1200, the voltage configuration module 1224 increases or decreases the voltages used by the APU 1202 and dGPU 1208. For example, for workloads that rely heavily on the dGPU 1208, such as complex graphics rendering, the voltage configuration module 1224 may increase the voltage applied to the dGPU 1208. For another example, for workloads that rely more heavily on the APU 1202 than the dGPU 1208, such as audio encoding, or when the computing device 1200 is in a low-power consumption state, the voltage configuration module 1224 may increase the voltage applied to the APU 1202. In some implementations, an increase in voltage to one component (e.g., to the APU 1202 and dGPU 1208) will result in a decrease in voltage to another component or an increase in voltage to one component may be performed in response to a decrease in voltage to another component.
[0066] In some implementations, modifying the voltage of a given component will result in a modification of the operating frequency of the given component, or the modification of the voltage of a given component will be performed in response to the modification of the operating frequency of the given component. For example, assume that a command or request to increase the operating frequency of dGPU 1208 is issued in response to presenting a job submitted to dGPU 1208. Voltage configuration module 1224 will then increase the voltage provided to dGPU 1208 so that dGPU 1208 can operate at the increased frequency. In some implementations, the frequency of a given component is defined according to a frequency-voltage curve. The frequency-voltage curve defines the relationship between the frequency of a component and the voltage corresponding to the component frequency. In other words, the frequency-voltage curve defines the corresponding voltage of the component for a given frequency.
[0067] Those skilled in the art will appreciate that the voltage configuration module 1224 operates within various constraints on voltage in the computing device 1200. For example, in some implementations, the APU 1202 and the dGPU 1208 have defined minimum and maximum safe voltages. Those skilled in the art will appreciate that the specific voltage limits for the APU 1202 and the dGPU 1208 depend on the specific cooling and thermal solutions implemented in the computing device 1200.
[0068] Those skilled in the art will also appreciate that the methods for component coolers described herein provide improved cooling capabilities for the APU 1202 and dGPU 1208, thereby allowing for increased maximum safe operating voltages for both the APU 1202 and the dGPU 1208. Thus, improvements in computing performance are achieved through the improved cooling methods described herein.
[0069] To explain further, Figure 13 A flow chart illustrating an exemplary method for component cooling according to some implementations is set forth. The method includes thermally coupling 1302 a first heat transfer element to a heat-generating electronic component. The method also includes thermally coupling 1304 a plurality of heat transfer paths between the first heat transfer element and a second heat transfer element. Each heat transfer structure in the plurality of heat transfer structures is configured to provide a separate heat conduction path from the first heat transfer element to the second heat transfer element. The method also includes providing 1306 a first portion of a heat transfer fluid in thermal contact with the first heat transfer element and a second portion of the heat transfer fluid in thermal contact with the second heat transfer element.
[0070] The exemplary embodiments of the present disclosure are primarily described in the context of a fully functional computer system for a component cooler for a computing device. However, readers familiar with the art will recognize that the present disclosure may also be embodied in a computer program product provided on a computer-readable storage medium for use with any suitable data processing system. Such computer-readable storage media may be any storage medium for machine-readable information, including magnetic media, optical media, or other suitable media. Examples of such media include magnetic disks in hard drives or floppy disks, optical disks in optical drives, magnetic tapes, and other media that may occur to those skilled in the art. Those skilled in the art will immediately recognize that any computer system with appropriate programming means will be able to perform the steps of the method of the present disclosure as embodied in a computer program product. Those skilled in the art will also recognize that although some of the exemplary embodiments described in this specification are directed to software installed and executed on computer hardware, alternative embodiments implemented as firmware or hardware are also within the scope of the present disclosure.
[0071] The present disclosure may be a system, method, and / or computer program product.The computer program product may include a computer-readable storage medium (or media) having computer-readable program instructions thereon for causing a processor to execute various aspects of the present disclosure.
[0072] A computer-readable storage medium can be a tangible device that can retain and store instructions for use by an instruction execution device. A computer-readable storage medium can be, for example, but not limited to, an electronic storage device, a magnetic storage device, an optical storage device, an electromagnetic storage device, a semiconductor storage device, or any suitable combination of the foregoing. An incomplete list of more specific examples of computer-readable storage media includes the following: a portable computer disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), a static random access memory (SRAM), a portable compact disc read-only memory (CD-ROM), a digital versatile disk (DVD), a memory stick, a floppy disk, a mechanically encoded device (such as a punched card or raised structure in a groove on which instructions are recorded), and any suitable combination of the foregoing. As used herein, a computer-readable storage medium cannot be understood as a transient signal per se, such as a radio wave or other freely propagating electromagnetic wave, an electromagnetic wave propagated by a waveguide or other transmission medium (e.g., a light pulse by a fiber optic cable), or an electrical signal transmitted by a wire.
[0073] The computer-readable program instructions described herein can be downloaded from a computer-readable storage medium to a corresponding computing / processing device, or downloaded to an external computer or external storage device via a network (e.g., the Internet, a local area network, a wide area network, and / or a wireless network). The network can include copper transmission cables, optical transmission fibers, wireless transmissions, routers, firewalls, switches, gateway computers, and / or edge servers. The network adapter card or network interface in each computing / processing device receives the computer-readable program instructions from the network and forwards the computer-readable program instructions to be stored in a computer-readable storage medium within the corresponding computing / processing device.
[0074] The computer-readable program instructions for performing the operation of the present disclosure can be assembly instructions, instruction set architecture (ISA) instructions, machine instructions, machine-related instructions, microcode, firmware instructions, state setting data or source code or object code written in any combination of one or more programming languages, and programming languages include object-oriented programming languages such as Smalltalk, C++, and conventional process programming languages such as "C" programming language or similar programming languages. The computer-readable program instructions can be executed entirely on the user's computer, partially on the user's computer, as an independent software package, partially on the user's computer and partially on a remote computer or entirely on a remote computer or server. In the latter case, the remote computer can be connected to the user's computer through any type of network (including local area network (LAN) or wide area network (WAN)), or can be connected to an external computer (for example, by using the Internet of an Internet service provider). In some specific implementations, the electronic circuit including, for example, a programmable logic circuit, a field programmable gate array (FPGA) or a programmable logic array (PLA) can execute computer-readable program instructions, specifically by utilizing the state information of the computer-readable program instructions to personalize the electronic circuit, so as to perform various aspects of the present disclosure.
[0075] Various aspects of the present disclosure are described herein with reference to flowchart illustrations and / or block diagrams of methods, apparatus (systems), and computer program products according to specific implementations of the present disclosure. It should be understood that each block of the flowchart illustrations and / or block diagrams, and combinations of blocks in the flowchart illustrations and / or block diagrams, can be implemented by computer-readable program instructions.
[0076] These computer-readable program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, or other programmable data processing device to obtain a machine, so that the instructions executed by the processor of the computer or other programmable data processing device form a means for implementing the functions / actions specified in one or more blocks of the flowchart and / or block diagram. These computer-readable program instructions can also be stored in a computer-readable storage medium that can instruct the computer, programmable data processing device, and / or other equipment to function in a specific manner, so that the computer-readable storage medium having the instructions stored therein includes an article of manufacture containing instructions for implementing various aspects of the functions / actions specified in one or more blocks of the flowchart and / or block diagram.
[0077] Computer-readable program instructions may also be loaded onto a computer, other programmable data processing apparatus, or other device, causing a series of operational steps to be performed on the computer, other programmable apparatus, or other device to obtain a computer-implemented process, such that the instructions executed on the computer, other programmable apparatus, or other device implement the functions / actions specified in one or more boxes of the flowchart and / or block diagram.
[0078] The flow chart and block diagram in the figure illustrate the possible specific implementation architecture, function and operation of the system, method and computer program product according to various specific implementations of the present disclosure. In this regard, each frame in the flow chart or block diagram may represent a module, segment or part of one or more executable instructions for realizing a specified logical function. In some alternative specific implementations, the function pointed out in the frame may not occur in the order pointed out in the figure. For example, depending on the function involved, the two frames shown in succession may actually be performed substantially simultaneously, or these frames may sometimes be performed in reverse order. It will also be noted that each frame in the block diagram and / or flow chart illustration and the combination of the frames in the block diagram and / or flow chart illustration can be implemented by a system based on dedicated hardware that performs a specified function or action or performs a combination of dedicated hardware and computer instructions.
[0079] It will be understood from the foregoing description that modifications and variations may be made in various embodiments of the present disclosure. The descriptions in this specification are for illustrative purposes only and should not be interpreted in a limiting sense. The scope of the present disclosure is limited only by the language of the appended claims.
Claims
1. A device for cooling a component, the device comprising: a first heat transfer element configured to be thermally coupled to a heat generating electronic component; a second heat transfer element; a plurality of heat transfer paths thermally coupled between the first heat transfer element and the second heat transfer element, each heat transfer path of the plurality of heat transfer paths being configured to provide a separate thermally conductive path from the first heat transfer element to the second heat transfer element; and A manifold includes a first fluid passage providing a first portion of a heat transfer fluid in thermal contact with the first heat transfer element and a second fluid passage providing a second portion of the heat transfer fluid in thermal contact with the second heat transfer element.
2. The apparatus of claim 1, wherein the heat-generating electronic component comprises a processor. 3 . The device of claim 1 , wherein the plurality of heat transfer paths comprises at least one heat pipe.
4. The device of claim 1, wherein the plurality of heat transfer paths comprises at least one vapor chamber. 5 . The device of claim 1 , wherein the first heat transfer element comprises at least one of a first substrate and a second substrate. 6 . The device of claim 5 , wherein a portion of the plurality of heat transfer paths is disposed between the first substrate and the second substrate.
7. The apparatus of claim 1, further comprising a first thermoelectric cooler thermally coupled to the first heat transfer element. 8 . The apparatus of claim 7 , further comprising a first cold plate, wherein the first thermoelectric cooler is configured to transfer heat from the first heat transfer element to the first cold plate.
9. The apparatus of claim 8, wherein the first fluid channel passes through the first cold plate.
10. The apparatus of claim 1, wherein the second heat transfer element comprises at least one of a third substrate and a fourth substrate. 11 . The device of claim 10 , wherein a portion of the plurality of heat transfer paths is disposed between the third substrate and the fourth substrate.
12. The apparatus of claim 1, further comprising a second thermoelectric cooler thermally coupled to the second heat transfer element. 13 . The apparatus of claim 12 , further comprising a second cold plate, wherein the second thermoelectric cooler is configured to transfer heat from the second heat transfer element to the second cold plate. The apparatus of claim 13 , wherein the second fluid channel passes through the second cold plate.
15. A device for cooling a component, the device comprising: a first heat transfer element configured to be thermally coupled to a heat generating electronic component; a second heat transfer element; a plurality of heat transfer paths thermally coupled between the first heat transfer element and the second heat transfer element, each heat transfer path of the plurality of heat transfer paths being configured to provide a separate thermally conductive path from the first heat transfer element to the second heat transfer element; and A cooling block includes a passageway for providing a heat transfer fluid in thermal contact with the first heat transfer element.
16. The apparatus of claim 15, further comprising a cooling fan assembly coupled to the second heat transfer element.
17. The apparatus of claim 15, wherein the heat-generating electronic component comprises a processor.
18. The apparatus of claim 15, wherein the plurality of heat transfer paths comprises at least one heat pipe.
19. The apparatus of claim 15, wherein the first heat transfer element comprises at least one of a first substrate and a second substrate.
20. The apparatus of claim 15, wherein the second heat transfer element comprises a cold plate.