The present invention relates to a general purpose graphic processing unit (GPGPU) carriers, and more specifically to compact and tool-less GPGPU carriers.
General purpose graphic processing units (GPGPUs) are commonly utilized to perform computation in applications traditionally handled by a central processing unit (CPU). Even a single GPU-CPU framework provides advantages that multiple CPUs on their own do not offer due to the specialization in each chip. While GPUs operate at lower frequencies, they typically have many times the number of cores. Thus, GPUs can effectively operate on pictures and graphical data far faster than a traditional CPU. Migrating data into graphical form, and then using the GPU to scan and analyze it, can result in profound speedup.
Removing a GPGPU from many types of computer systems today, requires tools and involves pulling cables from cable sockets. Overtime, or through incorrect usage, these cables or sockets become frail and can introduce data transfer errors associated with the GPGPU in use. Installing a GPGPU is not any easier because it involves similar hardships.
Furthermore, a computer data center (also referred to as an Internet data center or an enterprise data center) may contain a myriad of computer systems utilizing various GPGPUs. The large number of high-capacity GPGPUs in a data center poses significant problems associated with their removal and installation. The time and skills involved in removing or installing GPGPUs, without damage, in a data center can become burdensome.
Accordingly, it is becoming extremely important for various reasons (such as data backup and generally a GPGPU) to be able to easily, quickly, and efficiently remove and install a GPGPU in a computer system.
Embodiments of the invention concern compact and tool-less general purpose graphic processing unit (GPGPU) carriers. A computing device, according to the various embodiments, can include an enclosure with at least one slot; the at least one drive slot including a first locking element; and a second locking element configured to receive the GPGPU carrier. The computing device also includes the GPGPU carrier for removable insertion into the at least one slot.
The GPGPU carrier includes a bracket. The bracket includes a first receiving space for securing a first GPGPU. The bracket can also include a second receiving space for securing a second GPGPU. The bracket can also include a first latching mechanism configured to secure the first locking element of the slot, and a second latching mechanism configured to secure the second locking element of the slot. In some embodiments, the GPGPU carrier can include a frame secured to the bracket. In some embodiments, the frame can include a first end with a first guide slot configured, and a second end with a second guide slot configured, to secure the GPGPU carrier within the slot. The first and second guide slots are configured to enable the GPGPU carrier to adjust from a first position to a second position while secured within the slot.
In an exemplary embodiment of the computing device, the frame is secured to the bracket by at least one of fasteners, screws, and spot welding. In some embodiments of the computing device, the GPGPU carrier further comprises a PCIe interface connected to a PCIe cable. In some embodiments, the first locking mechanism and the second locking mechanism comprise a latch mechanism. In an alternative embodiment, the first locking mechanism and the second locking mechanism comprises a spring and lock mechanism. In some embodiments, the slot can include a connector for engaging a corresponding connector of the GPGPU carrier.
The present invention is described with reference to the attached figures, wherein like reference numerals are used throughout the figures to designate similar or equivalent elements. The figures are not drawn to scale, and they are provided merely to illustrate the instant invention. Several aspects of the invention are described below with reference to example applications for illustration. It should be understood that numerous specific details, relationships, and methods are set forth to provide a full understanding of the invention. One having ordinary skill in the relevant art, however, will readily recognize that the invention can be practiced without one or more of the specific details, or with other methods. In other instances, well-known structures or operations are not shown in detail to avoid obscuring the invention. The present invention is not limited by the illustrated ordering of acts or events, as some acts may occur in different orders and/or concurrently with other acts or events. Furthermore, not all illustrated acts or events are required to implement a methodology in accordance with the present invention.
As discussed above, there is significant interest in developing means to efficiently and reliably add or remove a GPGPU for a computer system. In particular, there is significant interest in developing means that: (1) do not require tools to install a GPGPU into a computer system; (2) minimize space requirements for the GPGPU in the computer system; and (3) reduce or eliminate instances of incorrect installation of the GPGPU, which can result in damage to the GPGPU, the computer system, or connectors there between.
In view of the foregoing, the present disclosure contemplates a GPGPU carrier design for a computer system and computer systems therefrom that address the foregoing requirements. In particular, the present disclosure contemplates: (1) a GPGPU carrier design that allows a technician to easily and reliably install a GPGPU in the GPGPU carrier; and (2) a corresponding drive slot design for a computer system that allows mechanical and electrical installation of the GPGPU in the computer system with minimal effort and training on the part of the technician. Such a design is illustrated in
The GPGPU carrier 100 and its components can be made of sheet metal using conventional metal fabrication techniques such as bending, forming, and stamping. As a result, the GPGPU carrier 100 can be made very inexpensively. Alternatively, the GPGPU carrier 100 and its components can be made of aluminum alloy, steel alloy, or any combination thereof. It should be realized that the GPGPU carrier 100 and its components can be made of any material constructed to withstand varying temperatures, and air flow of high velocity (from a plurality of fan modules not shown). The materials mentioned above are only for example, and not to limit this disclosure. A person having ordinary knowledge in the art may flexibly select any material in accordance with the disclosure.
The frame 105 can include a first end 106A and a second end 106B. Both the first end 106A and the second end 106B can be located at opposite distal ends of the frame 105. The first end 106A can include a first guide slot 107A. The second end 106B can include a second guide slot 107B. The first and second guide slots 107A and 107B are discussed in greater detail below. In alternative embodiments, the first end 106A can include other securing means. Further, the second end 106B can include other securing means. The GPGPU carrier 100 can also include a Peripheral Component Interconnect Express (“PCIe”) interface 101. The PCIe interface 101 can include an interface to connect to a PCIe cable (not shown). The PCIe cable (not shown) can be connected to a PCIe component (not shown) located remote. In some embodiments, the PCIe component is located within the server component of the GPGPU carrier 100. In alternative embodiments, the PCIe component is located remote from the server component of the GPGPU carrier 100.
Referring momentarily to
Referring momentarily to
Referring momentarily to
Referring back to
Referring momentarily to
Referring back to
In the embodiments discussed, the locking mechanism 303 (of
Referring momentarily to
Now that the configuration and operation of the GPGPU carrier 100 has been described, the disclosure now turns to a description of the configuration and operation of motherboard slot for receiving the GPGPU carrier 100.
In this configuration, the interaction of the latches 108A, 108B of the GPGPU carrier 100 and the locking mechanisms 303 (shown in
While various embodiments of the present invention have been described above, it should be understood that they have been presented by way of example only, and not limitation. Numerous changes to the disclosed embodiments can be made in accordance with the disclosure herein without departing from the spirit or scope of the invention. Thus, the breadth and scope of the present invention should not be limited by any of the above described embodiments. Rather, the scope of the invention should be defined in accordance with the following claims and their equivalents.
Although the invention has been illustrated and described with respect to one or more implementations, equivalent alterations and modifications will occur to others skilled in the art, upon reading and understanding this specification and the annexed drawings. In addition, while a particular feature of the invention may have been disclosed with respect to only one of several implementations, such feature may be combined with one or more other features of the other implementations, as may be desired and advantageous for any given or particular application.
The terminology used herein is for the purpose of describing particular embodiments only and is not intended to limit the invention. As used herein, the singular forms “a”, “an”, and “the” are intended to include the plural forms as well, unless the context clearly indicates otherwise. Furthermore, to the extent that the terms “including”, “includes”, “having”, “has”, “with”, or variants thereof are used in either the detailed description and/or the claims, such terms are intended to be inclusive in a manner similar to the term “comprising.”
Unless otherwise defined, all terms (including technical and scientific terms) used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this invention belongs. It will be further understood that terms, such as those defined in commonly used dictionaries, should be interpreted as having a meaning that is consistent with their meaning in the context of the relevant art and will not be interpreted in an idealized or overly formal sense unless expressly so defined herein.
This application is a Continuation of U.S. Non-Provisional application Ser. No. 15/807,337, entitled, “Compact Tool-Less General Purpose Graphic Processing Units (GPGPU) Carrier,” filed Nov. 8, 2017, the contents of which are incorporated by reference in their entirety as if fully set forth herein.
Number | Name | Date | Kind |
---|---|---|---|
6288911 | Aoki et al. | Sep 2001 | B1 |
6404641 | Fisk et al. | Jun 2002 | B1 |
9913394 | Blume et al. | Mar 2018 | B2 |
20040074082 | Kim et al. | Apr 2004 | A1 |
20050097580 | Lee | May 2005 | A1 |
20120127649 | Chen et al. | May 2012 | A1 |
20130027875 | Zhu et al. | Jan 2013 | A1 |
20140233182 | Demange | Aug 2014 | A1 |
20150123519 | Chen et al. | May 2015 | A1 |
20160021778 | Chen et al. | Jan 2016 | A1 |
20160042768 | Yang et al. | Feb 2016 | A1 |
20170293325 | Chen et al. | Oct 2017 | A1 |
Number | Date | Country |
---|---|---|
103593001 | Oct 2016 | CN |
201136490 | Oct 2011 | TW |
M470480 | Jan 2014 | TW |
Entry |
---|
TW Office Action for ApplicationNo. 107102240,dated Aug. 23, 2018,w/ First Office Action Summary. |
TW Search Report for ApplicationNo. 107102240,dated Aug. 23, 2018, w/ First Office Action. |
Corrected Notice of Allowance in U.S. Appl. No. 15/807,337, dated Oct. 3, 2018. |
Notice of Allowance in U.S. Appl. No. 15/807,337, dated Sep. 11, 2018. |
Number | Date | Country | |
---|---|---|---|
20190138066 A1 | May 2019 | US |
Number | Date | Country | |
---|---|---|---|
Parent | 15807337 | Nov 2017 | US |
Child | 16210981 | US |