摘要:
In a specific embodiment, a system for providing video is disclosed, the system having a system bus, which in one embodiment is an Advanced Graphics Port (AGP) bus. The system bus is connected to a data bridge, which is connected to a second and third AGP bus. Each of the AGP busses are connected to graphics processors. The bridge routes data requests from one graphics processor to the second graphics processor without accessing the system AGP bus based upon a memory mapping information stored in a routing table or a register set. In another aspect of the present invention, the bridge responds to initialization requests using attributes that may vary depending on the specific mode of operation. Another aspect of the present invention allows for conversion between various AGP protocol portions.
摘要:
In a specific embodiment, a system for providing video includes a system bus, which in one embodiment is an Advanced Graphics Port (AGP) busy. The system bus is connected to a data bridge, which is connected to a second and third AGP bus. Each of the AGP busses are connected to graphics processors. The bridge routes data requests from one graphics processor to the second graphics processor without accessing the system AGP bus based upon a memory mapping information stored in a routing table or a register set. In another aspect of the present invention, the bridge responds to initialization requests using attributes that may vary depending on the specific mode of operation. Another aspect of the present invention allows for conversion between various AGP protocol portions.
摘要:
In a specific embodiment, a system for providing video is disclosed, the system having a system bus, which in one embodiment is an Advanced Graphics Port (AGP) bus. The system bus is connected to a data bridge, which is connected to a second and third AGP bus. Each of the AGP busses are connected to graphics processors. The bridge routes data requests from one graphics processor to the second graphics processor without accessing the system AGP bus based upon a memory mapping information stored in a routing table or a register set. In another aspect of the present invention, the bridge responds to initialization requests using attributes that may vary depending on the specific mode of operation. Another aspect of the present invention allows for conversion between various AGP protocol portions.
摘要:
In a specific embodiment, a system for providing video is disclosed, the system having a system bus, which in one embodiment is an Advanced Graphics Port (AGP) bus. The system bus is connected to a data bridge, which is connected to a second and third AGP bus. Each of the AGP busses are connected to graphics processors. The bridge routes data requests from one graphics processor to the second graphics processor without accessing the system AGP bus based upon a memory mapping information stored in a routing table or a register set. In another aspect of the present invention, the bridge responds to initialization requests using attributes that may vary depending on the specific mode of operation. Another aspect of the present invention allows for conversion between various AGP protocol portions.
摘要:
In a specific embodiment, a system for providing video is disclosed, the system having a system bus, which in one embodiment is an Advanced Graphics Port (AGP) bus. The system bus is connected to a data bridge, which is connected to a second and third AGP bus. Each of the AGP busses are connected to graphics processors. The bridge routes data requests from one graphics processor to the second graphics processor without accessing the system AGP bus based upon a memory mapping information stored in a routing table or a register set. In another aspect of the present invention, the bridge responds to initialization requests using attributes that may vary depending on the specific mode of operation. Another aspect of the present invention allows for conversion between various AGP protocol portions.
摘要:
To minimize CPU processing requirements for preparing and transferring data to a graphics processor, a graphics command processor is provided that supports application-level commands and references to the data associated with these commands. The graphics command processor parses the application command and data reference parameters, and subsequently fetches the appropriate graphics data from memory directly, without requiring additional CPU resources. To optimize performance, the graphics command processor fetches the data in parallel with the parsing and processing of the application commands from the CPU. The graphics command processor also includes a processing unit that converts the data from the format used by the application program to the format used for rendering. The graphics command processor creates the commands and data sequences used by a graphics engine to render each object of the image. Because the graphics command processor is closely coupled with the graphics engine, a number of efficiency can be gained, particularly with regard to the transfer of related data items. The processing of the primitive graphic command and data sequences by the graphics engine is asynchronous with the receipt of subsequent commands from the CPU and the fetching of subsequent data associated with the commands from the memory. In this manner, the latency associated with the conventional sequential processing of graphics data is minimized.
摘要:
A method and apparatus for mapping a linear address to a tiled address that reduces latency between retrieval of pages of data is accomplished when a video graphics processor receives a linear address from the central processing unit and determines whether the linear address is referencing a tiled surface, which is one of up to four portions of the memory. If so, the video graphics processor obtains parameters of the tiled surface. Having obtained the parameters, the video graphics processor determines a normalized linear address based on at least one of the parameters and the linear address. Having done this, the video graphics processor determines a band pointer of the tiled surface based on at least one of the parameters, the normalized linear address and a modular function. In essence, the band pointer points to a normalized initial address of a band of a tiled surface, which includes a plurality of bands. Having obtained the band pointer, the video graphics processor then determines a linear band offset based on the band pointer and at least one of the parameters. Next, a tiled band offset is determined based on the linear band offset. Finally, the tiled address is determined based on the tiled band offset, the band pointer, and at least one of the parameters.
摘要:
A multiple device frame synchronization method and apparatus utilizes events completion signaling between multiple devices, such as multiple graphics processors. The signaling serves as a stall command for stalling graphics data rendering commands in a command FIFO of the rendering engine of a graphics processor in response to a rendering complete signal, or other event signal generated by the other graphics processor. Accordingly, the processor that, for example, completes a current frame relay is stalled until the other processor has completed its rendering function for a particular odd line, even line, entire frame or partial frame as desired.
摘要:
A central processor unit (CPU) is connected to a system/graphics controller generally comprising a monolithic semiconductor device. The system/graphics controller is connected to an input output (IO) controller via a high-speed PCI bus. The IO controller interfaces to the system graphics controller via the high-speed PCI bus. The IO controller includes a lower speed PCI port controlled by an arbiter within the IO controller. Generally, the low speed PCI arbiter of the IO controller will interface to standard 33 MHz PCI cards. In addition, the IO controller interfaces to an external storage device, such as a hard drive, via either a standard or a proprietary bus protocol. A unified system/graphics memory which is accessed by the system/graphics controller. The unified memory contains both system data and graphics data. In a specific embodiment, two channels, CH0 and CH1 access the unified memory. Each channel is capable of accessing a portion of memory containing graphics data or a portion of memory containing system data.
摘要:
A request for video or graphics data is made to a memory controller. When the memory controller determines a translation of the data must first be made, a request is made to a translator. The translator either translates the address or requests translation information from the memory controller. The memory controller accesses memory based upon the translator request. If the request is for translation data the results are tagged for the translator. If the translator request is for the translated address, the results are tagged for the original request.