TWM363648U - Plug-in graphics module architecture - Google Patents

Plug-in graphics module architecture


Publication number
TWM363648U TW98208537U TW98208537U TWM363648U TW M363648 U TWM363648 U TW M363648U TW 98208537 U TW98208537 U TW 98208537U TW 98208537 U TW98208537 U TW 98208537U TW M363648 U TWM363648 U TW M363648U
Prior art keywords
graphics module
processing unit
Prior art date
Application number
Other languages
Chinese (zh)
Min-Chuan Wan
Original Assignee
Xgi Technology Inc
Priority date (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.)
Filing date
Publication date
Application filed by Xgi Technology Inc filed Critical Xgi Technology Inc
Priority to TW98208537U priority Critical patent/TWM363648U/en
Publication of TWM363648U publication Critical patent/TWM363648U/en



The present invention provides a method for a plug-in graphics module, comprising the first graphics processing unit (GPU) couples to a low voltage differential signaling (LVDS) channel, the graphics module electrically connected to a north bridge. The bridge circuit is capable of transmitting a plurality of data to the graphics module, receiving a processed result from the graphics module, and transmitting the processed result to the memory device for the GPU to access the processed result, and then the GPU outputs the processed result to a panel through the differential signal bus when the graphics module is plugged in the connecter.


M363648 V. New description: [New technical field] The present invention relates to a system including a graphics processing unit, and more particularly to a system including a replaceable graphics processing unit. [Prior Art] Referring to Figure 1, a conventional method for improving the graphics processing capability of a computing system, such as a desktop computer, is exemplified. The north bridge 101 is an interface for accessing the CPU, and sends graphics data to the graphics processing units (GPUs) 102 and 103. GPUs 102 and 103 process graphics data simultaneously. Obviously, multi-GPU systems are better than single GPU systems. The processed graphic data is displayed on the display 1〇5.

Both NvidiaSLI and AtiCrossFire use the same architecture described above. Both GPUs must be from the same brand, and must even be limited to certain Gpu products; in addition, this architecture can only operate under certain Northbridges, for example: NVidmGef〇rce6800 needs to be combined with its SLI chipset Dual Gpu works. Furthermore, the aforementioned hybrids require additional connecting lines, connections, or conversion chips. Referring next to Figure 2, an alternative method, such as a notebook computer, is used to illustrate how conventional methods can enhance performance. Gpm〇2 is the original graphics processing component of a notebook with poor performance. The 匕 (4) channel 207 connected to _2 〇 2 is the path through which the GPU 202 transmits graphics data to the lvds panel. The coffee move may be integrated into the North Bridge 2〇1 or an independent component independent of the North Bridge view. The M363648 graphics module 203 is a replaceable component that includes a better performing GPU (not shown). When the graphics module 203 is inserted into the connector 206, the LVDS channel 2〇7 stops operating, the GPU 202 no longer receives graphics data from the north bridge 2〇1, and the graphics memory of the GPU 202, such as the integrated memory platform (IGp) in the main memory. The shared memory (sharedmemory) or the independent Gpu's physical drawing memory - (localframebuffer, not shown) does not work either. VBI〇s, which are stored in - Flash, EEPROM, or other storage components (not shown) associated with GpU2〇2, are no longer active. The north bridge 201 transmits the graphic data to the graphic module 2 through the connector 2〇6 for processing. The processed graphics data is transmitted to the LVDS panel 205 through the connector 2〇6 and the LV〇s channel 2〇4.

The NvidiaMXM and ATiAXI(R) platforms use the above architecture. Because different LVDS panels need to be adjusted through VBI〇s to achieve the correct timing and resolution, the VBI〇s of the GPU on the graphics module 203 must be adjusted and updated, which requires special software and panel information. And experienced technicians. Even so, it takes a long time to retreat and retreat as if it were a recording period. For the average user, it is almost impossible to add additional _ modules by themselves and adjust the VBIOS by themselves. 'So it is necessary to propose a flexible architecture for the user, which has the opportunity to enhance the performance of the processing without worrying about the GPU and chipset brands and models purchased, and not bothering how Adjust the smart s or buy the amount ^ hardware. [New content] M363648. The purpose of the present invention is to provide an architecture that enhances the processing capabilities of the Lanna system without having to adjust the VBI〇s. Another purpose of the new type of 匕力t is to provide an enhanced LVDS system for graphics processing. The moon-wood frame does not have to take into account 01>1; and the bridge circuit and the model or the hardware to be added. Another object of the present invention is to provide an architecture that allows the user to enhance the graphics processing functions of the LVDS system. To achieve the above objectives, the architecture includes a connector '- which is connected to the LVDS channel and the north bridge. When a graphics module is plugged into this connector, the _ module is automatically connected to the north bridge through the connector. Thus the graphics module can receive the _ data from the North Bridge. The graphics module processes the data and then conveys the processed stomach material to the key, such as - entity_memory or main memory, the GPU reads the processed data on the memory, and then uses the original (10) $ channel transfer, displayed on the LVDS panel. The features and advantages of the present invention will be apparent from the following description of the preferred embodiments. Figure; cut and apply for a full-time division to make a clearer explanation. [Embodiment] - Embodiment, reference to Fig. 3' is a block diagram according to the present invention. The north bridge 3〇1 is a portion of the bridge circuit (not shown) used to access the cpu of the computing system (not shown). GPU 302 is integrated into Northbridge 301. Or in another embodiment, Gpu3〇2 is a separate component that is independent of Northbridge 301. Whether integrated in Northbridge 3〇1 or M363648® independent of Northbridge 301, GPU 302 includes LVDS channel 307 as an output to the LVDS panel. A storage component (not shown), such as Flash or EEpRoM, acts as an element for storing the VBIOS of GPU 302. The GPU 302's VBIOS control GP1B〇2 and the LVDS panel 305 connected to the LVDS channel 3〇7 also store information about the LVDS panel. A graphics module 3〇3 including a GPU (not shown) is a replaceable component. The graphic module 303 may include a physical drawing memory and a storage device associated with the vbi〇s of the graphic module. The connector is electrically connected to the North Bridge 3〇ι. The graphics module tears the insertion connection 5306' GPU 302 to no longer receive graphics data from Northbridge 3()1, and the graphics data is transferred to graphics module 303 instead of GpU3〇2. Therefore, the north bridge 3〇 transmits the graphic data to the graphic module through the connector 306. 3ό3 ό Figure ▲ group 303, lightly transmitted the processed data back to the north bridge 3 to the memory ( Not shown), for example, GpU3〇2 _picture memory or main memory. The GPU is read _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ Since the Lv〇s channel 3〇7 is used to transmit data to the LVDS panel milk, and the original Gp requested V Cong to store the correct timing and resolution of the LVDS panel 3〇5, there is related information, no matter the picture rabbit What is the VBIOS of group 303, the processed graphics data can be correctly displayed on the LVDS panel 3〇5 via the ^ side channel 307. Referring to Figure 4, there is shown a flow chart for processing graphics data in accordance with the present invention. Step ‘Northbridge transmits the data to the graphics module for processing. The next step is to say that the graphics module transports the processed data back to the North Bridge. In the next step, the North Bridge transmits the memory of the 7 M363648 to the German body, and the main memory. Next step 440 The GPU receives the processed data from this memory. In the next step, the GPU outputs the processed resource, such as a panel. The foregoing description of the preferred embodiments of the present invention is intended to be illustrative and illustrative. The invention is not intended to be exhaustive or to limit the invention. Obviously many repairs will be apparent to those skilled in the art. The embodiment was chosen and described in order to better explain the principles of the present invention and the best mode of the application of the present invention, which will allow the skilled in the art to understand the novel embodiments of the various embodiments. Covers various modifications of the implementation. The present invention is intended to be construed as being limited to the scope of the invention and the equivalents thereof, unless otherwise claimed. The present invention can be modified by a person skilled in the art without departing from the scope of the invention as defined by the following claims. Furthermore, in this disclosure, there are no components and components that are _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ In addition, the abstract of this disclosure provides a detailed description of the application. It should be understood that it is turned over or limited. [Simple Description of the Drawing] Figure 1 illustrates a conventional method for enhancing the graphics processing performance of a computer system. Figure 2 illustrates another conventional method of enhancing graphics processing performance in a computer system. M363648 Figure 3 illustrates a block diagram designed in accordance with the present invention. Figure 4 illustrates a flow chart implemented in accordance with the present invention. [Main component symbol description]

101 Northbridge 102 GPU 103 GPU 105 Display 201 North Bridge 202 GPU 203 Graphics Module 204 LVDS Channel 205 LVDS Panel 206 Connector 207 LVDS Channel 301 North Bridge 302 GPU 303 Graphics Module 305 LVDS Panel 306 Connector 307 LVDS Channel 410 North Bridge Transfer to Graphics Module 420 Graphics Module Transfer to North Bridge M363648 430 North Bridge Transfer to Memory 440 440 GPU Read Memory 450 GPU Transfer to Panel ίο

Claims (1)

  1. M363648 VI. Scope of Application: 1. An architecture for a companion graphics processing unit, comprising: a graphics processing unit (GPU) capable of processing graphics data; a connector capable of connecting a graphics module; a circuit, connected to the GPU and the connector; and a differential signal bus, electrically connected to the GPU, wherein when the graphics module is processed, the _module is generated according to the materials The processed result, the graphics module transmits the _result to the memory component for the clerk to access the processed result, and the GPU outputs the processed result to a panel through the differential surface stream . The architecture of the companion graphics processing unit, as described in claim 1, wherein the coffee is integrated into the bridge circuit. 3. The architecture of a companion graphics processing unit as described by the requester, wherein which is independent of the bridging circuit. 4. If requested! The architecture of the companion graphics processing unit, wherein the bridge circuit is a chip set. 11
TW98208537U 2006-05-12 2006-05-12 Plug-in graphics module architecture TWM363648U (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
TW98208537U TWM363648U (en) 2006-05-12 2006-05-12 Plug-in graphics module architecture

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
TW98208537U TWM363648U (en) 2006-05-12 2006-05-12 Plug-in graphics module architecture

Publications (1)

Publication Number Publication Date
TWM363648U true TWM363648U (en) 2009-08-21



Family Applications (1)

Application Number Title Priority Date Filing Date
TW98208537U TWM363648U (en) 2006-05-12 2006-05-12 Plug-in graphics module architecture

Country Status (1)

Country Link
TW (1) TWM363648U (en)

Cited By (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
TWI547811B (en) * 2014-05-30 2016-09-01 蘋果公司 Selective gpu throttling

Cited By (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
TWI547811B (en) * 2014-05-30 2016-09-01 蘋果公司 Selective gpu throttling

Similar Documents

Publication Publication Date Title
US9652194B2 (en) Cable with video processing capability
US6317352B1 (en) Apparatus for implementing a buffered daisy chain connection between a memory controller and memory modules
US5535340A (en) Method and apparatus for maintaining transaction ordering and supporting deferred replies in a bus bridge
EP0422103B1 (en) I/o bus to system bus interface
TWI331299B (en) Command parsers, methods therefor, and graphic processing units using the same
US6477614B1 (en) Method for implementing multiple memory buses on a memory module
JP3786120B2 (en) Data transfer control device and electronic device
US6845420B2 (en) System for supporting both serial and parallel storage devices on a connector
US7793029B1 (en) Translation device apparatus for configuring printed circuit board connectors
JP2014029532A (en) Display system having frame reuse using division multi-connector element differential bus connector
US7882296B2 (en) Deadlock avoidance in a bus fabric
US5799204A (en) System utilizing BIOS-compatible high performance video controller being default controller at boot-up and capable of switching to another graphics controller after boot-up
JP5529748B2 (en) Video rendering on high-speed peripheral interconnect bus
JP4327175B2 (en) Multi-graphics processor system, graphic processor and drawing processing method
US7761624B2 (en) Systems and apparatus for main memory with non-volatile type memory modules, and related technologies
US7603501B2 (en) Communication circuit of serial peripheral interface devices
US7761625B2 (en) Methods for main memory with non-volatile type memory modules, and related technologies
JP3384571B2 (en) Multi-mode home terminal system and method for processing video / graphics information
TWI341978B (en) Connecting graphics adapters for scalable performance
US9229859B2 (en) Mapping non-prefetchable storage locations into memory mapped input/output space
US8066515B2 (en) Multiple graphics adapter connection systems
US8417838B2 (en) System and method for configurable digital communication
US5732224A (en) Computer system having a dedicated multimedia engine including multimedia memory
US6052133A (en) Multi-function controller and method for a computer graphics display system
US7721118B1 (en) Optimizing power and performance for multi-processor graphics processing

Legal Events

Date Code Title Description
MK4K Expiration of patent term of a granted utility model