The field of invention pertains generally to the electrical arts, and, more specifically, to a DIMM cooling assembly with heat spreader anti-rotation mechanism.
The continued reduction of transistor minimum feature size has resulted in tremendous numbers of transistors being integrated on a single logic chip. As a consequence, logic chip computational ability is reaching extremely high levels (e.g., as demonstrated by artificial intelligence implementations). Generally, logic chip computations use memory as a data scratch pad, data store and/or instruction store (for those logic chips that execute instructions in the case of the later). As logic chip computational ability continues to expand, the bandwidth and storage capacity of the memory used to support logic chip operation will likewise need to expand. The increase in memory performance likewise increases memory power dissipation which presents system engineering with memory chip cooling solution challenges.
The flat, planar heat spreaders 101_1, 101_2, ideally, make flush contact with and press into the package lids of the semiconductor chips thereby creating a low thermal resistance path from the chip package lids to the heat spreaders 101_1, 101_2. The heat spreaders 101_1, 101_2 are composed of a thermally conductive material (e.g., a metal such as aluminum or copper).
With a low resistance thermal path between the chips and the heat spreaders 101_1, 101_2, heat generated by the chips is transferred to the heat spreaders 101_1, 101_2 with sufficient efficiency. The heat spreaders 101_1, 101_2 have a large surface area contact with the ambient that surrounds the DIMM 100, thus, heat is more efficiently transferred from the chips to the DIMM's ambient with the heat spreaders 101_1, 101_2 in place.
The heat spreaders 101_1, 101_2 are aligned to the DIMM 100 through the use of a tab 103 at the edge of one of the heat spreaders 101_1 that extends through a corresponding set of notches 104 in the DIMM circuit board and the other heat spreader 101_2. A set of such tabs and corresponding notches exist at both ends of the DIMM and, when engaged, effect lateral alignment of both heat spreaders 101_1, 101_2 and the DIMM circuit board.
As discussed above, ideally, the heat spreaders 101_1, 101_2 press into the package lids of the semiconductor chips to effect a low thermal resistance between the package lids and the heat spreaders. Here, C-shaped clips 105 are fitted over both heat spreaders 101_1, 101_2. The spring-like resistance of the clips 105 to being fitted over both heat spreaders 101_1, 101_2 presses the heat spreaders 101_1, 101_2 towards one another and into the package lids of the their respective DIMM sides.
Referring to
Again, as with the prior art approach, one or more C shaped “clips” 205a, 205b can be used to press both heat spreaders 201 into their respective DIMM sides (
Unfortunately, when the arms of the clips 205a,b are placed over the heat spreaders and the C shaped spine of the clips 205a,b open outwardly, the expanded distance 210 of the heat spreaders and/or clip 205b can result in misalignment off the heat spreaders 201 on the DIMM and/or the DIMM within its DIMM socket. Specifically, the inward force exerted by the short arm clip 205a effects a higher axis of rotation 211 about which a heat spreader 201_2 can rotate away 212 from its package lid surfaces, whereas, the long arm clip 205b effects a lower axis of rotation 213 about which a heat spreader 201_2 can rotate away 214 from its package lid surfaces. The rotation 213, 214 results in air gaps between the heat spreader 201_2 and increased thermal resistance between the heat spreader 201_2 and the chip package lids it is supposed to press into.
If a loading mechanism 315 is used instead of a retention clip, as observed in
The thicker metal 316 heat spreaders further reduces the thermal resistance between the chip package lids and the heat spreaders (the heat spreaders have greater thermal mass and will therefore draw more heat from the semiconductor chip packages). Moreover, with the heat spreaders being mechanically integrated with the heat sink fins 317, the surface area contact of the overall structure with the ambient is increased which further improves heat transfer from the memory chips to the ambient.
Ideally the heat spreader structure 317 is centered along the vertical axis of the DIMM so that the weight of the heat spreader structure 317 and heat spreaders are distributed evenly on both sides of the DIMM.
Unfortunately, if a heat spreader rotates 312 when the loading mechanism 315 is tightened as described above, the rotation 312 can place the entire DIMM and heat spreader assembly out of balance. As a consequence, the DIMM can rotate 318 within its socket and create a bad electrical connection between the DIMM and the motherboard it is plugged into.
A solution, as observed into
Here, whereas the previously discussed solutions only created a compressive force above the DIMM's circuit board to press the heat spreaders into their respective DIMM sides, by contrast, the improved approach of
However, to the extent such a compressive force above the DIMM circuit board 402 induces either or both of the heat spreaders 401_1, 401_2 to rotate outward away from the DIMM circuit board 402, such inducement is largely nullified (e.g., blocked) by the presence of compressive force 403 mechanisms that are located at the DIMM edges. Notably, the compressive force is applied, e.g., approximately half way up 404 along the height of the DIMM circuit board 402 to apply a sufficient counteractive torque against heat spreader rotation about an axis 405 that exists above the DIMM circuit board 402. That is the, the distance 406 from the axis of rotation 405 above the DIMM circuit board 402 to the point of application of the compressive force 403 against the heat spreaders 401_1401_2 creates a substantial lever arm that counter acts the rotation.
With respect to the precise compressive force mechanism, according to a first approach observed in
As alluded to above, the holes 503 are positioned at a low enough height 504 along the side of the DIMM circuit board 502 to create a substantial counter-torque to any outward rotational force experienced by the heat spreaders 501_1, 501_2. As such, in alternative embodiments, the holes 503 are not placed in immediate proximity of the lateral alignment tabs and notches (e.g., the holes 503 can be placed further down (to a lower height) along the DIMM edge).
In further embodiments, two or more sets of through holes are placed at each DIMM edge to effect an even greater compressive force 403 (e.g., at each DIMM edge that are two or more tightened screws to substantially prevent outward heat spreader rotation).
In alternative or combined approaches clips are placed at the DIMM edges. Such clips can be placed instead of, or in conjunction, with the aforementioned through holes and their corresponding screws.
It is to be understood that the improvements described just above with respect to
The improved DIMM cooling assembly described above can be integrated into various electronic systems such as a networking system (e.g., switch, router, etc.) or computing system.
The improved DIMM cooling assembly described above can be applied to various kinds of DIMMs including not only DIMMs that include dynamic random access memory (DRAM) memory chips but also DIMMs that include non-volatile, three-dimensional (monolithically stacked on a same memory die) memory cell memory chips (e.g., flash), as well as DIMMs that include non-volatile, three-dimensional, resistive storage cell, byte addressable memory chips (e.g., Optane™ memory from Intel corporation).
An applications processor or multi-core processor 750 may include one or more general purpose processing cores 715 within its CPU 701, one or more graphical processing units 716, a main memory controller 717 and a peripheral control hub (PCH) 718 (also referred to as I/O controller and the like). The general purpose processing cores 715 typically execute the operating system and application software of the computing system. The graphics processing unit 716 typically executes graphics intensive functions to, e.g., generate graphics information that is presented on the display 703. The main memory controller 717 interfaces with the main memory 702 to write/read data to/from main memory 702. The power management control unit 712 generally controls the power consumption of the system 700. The peripheral control hub 718 manages communications between the computer's processors and memory and the I/O (peripheral) devices.
Other high performance functions such as computational accelerators, machine learning cores, inference engine cores, image processing cores, infrastructure processing unit (IPU) core, etc. can also be integrated into the computing system.
Each of the touchscreen display 703, the communication interfaces 704-707, the GPS interface 708, the sensors 709, the camera(s) 710, and the speaker/microphone codec 713, 714 all can be viewed as various forms of I/O (input and/or output) relative to the overall computing system including, where appropriate, an integrated peripheral device as well (e.g., the one or more cameras 710). Depending on implementation, various ones of these I/O components may be integrated on the applications processor/multi-core processor 750 or may be located off the die or outside the package of the applications processor/multi-core processor 750. The computing system also includes non-volatile mass storage 720 which may be the mass storage component of the system which may be composed of one or more non-volatile mass storage devices (e.g., hard disk drive, solid state drive, etc.). The non-volatile mass storage 720 may be implemented with any of solid state drives (SSDs), hard disk drive (HDDs), etc.
Embodiments of the invention may include various processes as set forth above. The processes may be embodied in program code (e.g., machine-executable instructions). The program code, when processed, causes a general-purpose or special-purpose processor to perform the program code's processes. Alternatively, these processes may be performed by specific/custom hardware components that contain hard wired interconnected logic circuitry (e.g., application specific integrated circuit (ASIC) logic circuitry) or programmable logic circuitry (e.g., field programmable gate array (FPGA) logic circuitry, programmable logic device (PLD) logic circuitry) for performing the processes, or by any combination of program code and logic circuitry.
Elements of the present invention may also be provided as a machine-readable medium for storing the program code. The machine-readable medium can include, but is not limited to, floppy diskettes, optical disks, CD-ROMs, and magneto-optical disks, FLASH memory, ROMs, RAMs, EPROMs, EEPROMs, magnetic or optical cards or other type of media/machine-readable medium suitable for storing electronic instructions.
In the foregoing specification, the invention has been described with reference to specific exemplary embodiments thereof. It will, however, be evident that various modifications and changes may be made thereto without departing from the broader spirit and scope of the invention as set forth in the appended claims. The specification and drawings are, accordingly, to be regarded in an illustrative rather than a restrictive sense.
Number | Date | Country | Kind |
---|---|---|---|
PCT/CN2022/130760 | Nov 2022 | CN | national |
This application claims the benefit of priority to Patent Cooperation Treaty (PCT) Application No. PCT/CN2022/130760 filed Nov. 9, 2022. The entire content of that application is incorporated by reference.