Accelerated graphics port for a multiple memory controller computer system
원문보기
IPC분류정보
국가/구분
United States(US) Patent
등록
국제특허분류(IPC7판)
G09G-005/39
G09G-005/36
G06F-015/76
G06F-013/14
G06F-012/10
출원번호
US-0776439
(2004-02-10)
발명자
/ 주소
Jeddeloh,Joseph
출원인 / 주소
Micron Technology, Inc.
대리인 / 주소
Knobbe Martens Olson &
인용정보
피인용 횟수 :
5인용 특허 :
95
초록▼
An architecture for storing, addressing and retrieving graphics data from one of multiple memory controllers. In a first embodiment of the invention, one of the memory controllers having an accelerated graphics port (AGP) includes a set of registers defining a range of addresses handled by the memor
An architecture for storing, addressing and retrieving graphics data from one of multiple memory controllers. In a first embodiment of the invention, one of the memory controllers having an accelerated graphics port (AGP) includes a set of registers defining a range of addresses handled by the memory controller that are preferably to be used for all AGP transactions. The AGP uses a graphics address remapping table (GART) for mapping memory. The GART includes page table entries having translation information to remap virtual addresses falling within the GART range to their corresponding physical addresses. In a second embodiment of the invention, a plurality of the memory controllers have an AGP, wherein each of the plurality of the memory controllers supplies a set of registers defining a range of addresses that is preferably used for AGP transactions. In a third embodiment of the invention, a plurality of memory controllers implemented on a single chip each contain an AGP and a set of configuration registers identifying a range of addresses that are preferably used for AGP transactions.
대표청구항▼
What is claimed is: 1. A multiple memory controller system, comprising: at least two memory controllers for controlling a main memory, wherein a first of the at least two memory controllers is directly connected to a central processing unit bus, a bus supporting a peripheral device, and the main me
What is claimed is: 1. A multiple memory controller system, comprising: at least two memory controllers for controlling a main memory, wherein a first of the at least two memory controllers is directly connected to a central processing unit bus, a bus supporting a peripheral device, and the main memory, wherein each of the at least two memory controllers is configured to communicate with a central processing unit via the central processing unit bus, wherein each of the memory controllers are independent of the central processing unit, and also wherein the first of the at least two memory controllers comprises an accelerated graphics port for establishing a dedicated, point-to-point connection between the first of the at least two memory controllers and an accelerated graphics processor. 2. The system of claim 1, wherein the first of the at least two memory controllers defines a range of addresses in memory that are preferentially used over other addresses for storage of graphics data for transactions associated with the dedicated point-to-point connection. 3. The system of claim 1, wherein at least two of the at least two memory controllers are manufactured on the same chip. 4. The system of claim 1, wherein the first of the at least two memory controllers maintains a graphical address remapping table comprising at least one page table entry (PTE) providing information for translation of a virtual address to a physical address, wherein the virtual address includes a first portion and a second portion, the first portion corresponding to a PTE in the graphical address remapping table and wherein the second portion and information provided by the PTE are combined to provide the physical address. 5. The system of claim 4, wherein the first portion comprises a virtual page number field. 6. The system of claim 4, wherein the second portion comprises an offset field. 7. The system of claim 4, wherein the graphical address remapping table is configured by loading at least one configuration register during boot up of a computer system. 8. The system of claim 7, additionally comprising one configuration register includes a starting address of the graphical address remapping table. 9. The system of claim 7, wherein the at least one configuration register includes a boundary address defining the lowest address of a graphical address remapping table range. 10. The system of claim 7, wherein the at least one configuration register includes a range register defining the amount of memory that is preferentially used over other addresses for storage of graphics data for accelerated graphic port transactions. 11. The system of claim 7, wherein an initialization BIOS loads the at least one configuration register. 12. The system of claim 7, wherein an operating system API loads the at least one configuration register. 13. The system of claim 1, wherein the one of the at least two memory controllers and a memory are on a single semiconductor chip. 14. A computer, comprising: at least one accelerated graphics processor; and at least two memory controllers for controlling a main memory, wherein a first of the at least two memory controllers is directly connected to a central processing unit bus, a bus supporting a peripheral device, and the main memory, wherein each of the at least two memory controllers is configured to communicate with a central processing unit via the central processing unit bus, wherein each of the memory controllers are independent of the central processing unit, and wherein the first of the at least two memory controllers comprises an accelerated graphics port for establishing a dedicated point-to-point connection between the first of the at least two memory controllers and the accelerated graphics processor. 15. The system of claim 14, wherein the first of the at least two memory controllers defines a range of addresses that are preferentially used over other addresses for storage of graphics data for transactions associated with the dedicated point-to-point connection. 16. The computer of claim 14, wherein at least two of the at least two memory controllers include an accelerated graphics port. 17. The computer of claim 14, wherein at least two of the at least two memory controllers are included on the same chip. 18. The computer of claim 14, further comprising a graphical address remapping table residing on a memory connected to said first of the at least two memory controllers. 19. The computer of claim 18, wherein the graphical address remapping table is configured by loading at least one configuration register during boot up of a computer system. 20. The computer of claim 18, additionally comprising at least one configuration register that includes a starting address of the graphical address remapping table. 21. The computer of claim 18, wherein the at least one configuration register includes a boundary address defining the lowest address of a graphical address remapping table range. 22. The computer of claim 18, wherein an initialization BIOS loads the at least one configuration register. 23. The computer of claim 18, wherein an operating system API loads the at least one configuration register. 24. The computer of claim 14, further comprising a graphical address remapping table residing on said first of the at least two memory controllers, wherein the graphical address remapping table comprises at least one page table entry (PTE) providing information for translation of a virtual address to a physical address, wherein the virtual address includes a first portion and a second portion, the first portion corresponding to a PTE in the graphical address remapping table and wherein the second portion and the information provided by the PTE are combined to provide the physical address. 25. The computer of claim 14, wherein the first portion comprises a virtual page number field. 26. The computer of claim 14, wherein the second portion comprises an offset field. 27. The computer of claim 14, wherein said first of the at least two memory controllers and a memory are on a single semiconductor chip. 28. A multiple memory controller computer comprising: means for transmitting data to at least two memory controllers that each control a main memory wherein a first of the at least two memory controllers is directly connected to a central processing unit bus, a bus supporting a peripheral device, and the main memory, and wherein each of the at least two memory controllers is configured to communicate with a central processing unit via the central processing unit bus, wherein each of the memory controllers are independent of the central processing unit; and means for providing a dedicated point-to-point connection between a graphics accelerator and a first of the at least two memory controllers. 29. The computer of claim 28, and wherein the first of the at least two memory controllers defines a range of addresses that is preferentially used over other addresses for storage of graphics data for transactions associated with the dedicated point-to-point connection. 30. The computer of claim 28, further comprising means for controlling a graphical address remapping table having at least one page table entry (PTE) providing information for a translation of a virtual address to a physical address, wherein the virtual address includes a first portion and a second portion, the first portion corresponding to a PTE in the graphical address remapping table and wherein the second portion and information provided by the PTE are combined to provide the physical address. 31. The computer of claim 30, wherein the first portion comprises a virtual page number field. 32. The computer of claim 30, wherein the second portion comprises an offset field. 33. The computer of claim 30, wherein the physical address references a location in a memory. 34. The computer of claim 33, wherein an initialization BIOS loads said at least one configuration register. 35. The computer of claim 33, wherein an operating system API loads said at least one configuration register. 36. The computer of claim 30, wherein the graphical address remapping table is configured by loading said at least one configuration register during boot up of a computer system. 37. The computer of claim 28, additionally comprising at least one configuration register that includes a starting address of the graphical address remapping table. 38. The computer of claim 35, wherein the at least one configuration register includes a boundary address defining the lowest address of a graphical address relocation table range. 39. The computer of claim 35, wherein said at least one configuration register includes a range register defining the amount of memory that is preferentially used over other addresses for storage of graphics data for transactions associated with the dedicated point-to-point connection. 40. A method of using a multiple memory controller computer, comprising: controlling a main memory with at least two memory controllers, wherein a first memory controller is connected to an accelerated graphics processor via a dedicated point-to-point connection, and wherein the first of the at least two memory controllers is directly connected to a central processing unit bus, a bus supporting a peripheral device, and the main memory, wherein each of the at least two memory controllers is configured to communicate with a central processing unit via the central processing unit bus, wherein each of the memory controllers are independent of the central processing unit; and defining a group of addresses in the main memory that are preferentially used over other addresses for storage of graphics data for transactions associated with the dedicated point-to-point connection. 41. The method of claim 40, further comprising the act of controlling a graphical address remapping table having at least one page table entry (PTE) which provides information for a translation of a virtual address to a physical address, wherein the virtual address includes a first portion and a second portion, the first portion corresponding to a PTE in the graphical address remapping table and wherein the second portion and information provided by the PTE are combined to provide the physical address. 42. The method of claim 41, further comprising allocating a virtual page number field to the first portion. 43. The method of claim 41, further comprising allocating an offset field to the second portion. 44. The method of claim 41, further comprising loading said at least one configuration register during boot up of a computer system. 45. The method of claim 44, further comprising defining in a base address register the starting point of memory preferentially used over other addresses for storage of graphics data for transactions associated with the dedicated point-to-point connection. 46. The method of claim 44, further comprising setting a boundary address register defining the lowest address of the graphical address remapping table. 47. The method of claim 44, further comprising using a range register in the at least one configuration register to define the amount of memory that is preferentially used over other addresses for storage of graphics data for transactions associated with the dedicated point-to-point connection. 48. The method of claim 44, further comprising using an initialization BIOS to load said at least one configuration register. 49. The method of claim 44, further comprising using the operating system API to load said at least one configuration register. 50. The method of claim 40, further comprising manufacturing said at least two memory controllers and a memory on a single semiconductor chip.
연구과제 타임라인
LOADING...
LOADING...
LOADING...
LOADING...
LOADING...
이 특허에 인용된 특허 (95)
Mumford, Christopher J., Accelerated graphics display method.
Fukushima Tadashi (Hitachi JPX) Matsuo Shigeru (Hitachi JPX) Yoshida Shoji (Zama JPX) Komagawa Tooru (Hitachi JPX), Address-translatable graphic processor, data processor and drawing method with employment of the same.
Mehring Peter A. (Wilmington MA) Becker Robert D. (Shirley MA), Apparatus and method for a space saving translation lookaside buffer for content addressable memory.
Luan Chung-Chen ; Chong Siu-Ming ; Wang James H. ; Wong John ; Yeh Gong-Jong, Apparatus and method for implementing a programmable shared memory with dual bus architecture.
Becker Robert (Shirley MA) Mehring Peter (Wilmington MA), Apparatus for increasing the number of hits in a translation lookaside buffer including instruction address lookaside re.
Kelly Edmund (San Jose CA) Cekleov Michel (Mountain View CA) Dubois Michel (Los Angeles CA), Apparatus for maintaining consistency in a multiprocessor computer system using virtual caching.
Merrell Quinn ; Wang Wen-Hann, Backward inquiry to lower level caches prior to the eviction of a modified line from a higher level cache in a micropro.
Taylor George S. (Menlo Park CA) Farmwald P. Michael (Berkeley CA) Layman Timothy P. (San Carlos CA) Ngo Huy X. (Santa Clara CA) Roberts Allen W. (Union City CA), Cache memory system employing virtual address primary instruction and data caches and physical address secondary cache.
Horan Ronald Timothy ; Thome Gary W. ; Olarig Sompong, Computer bridge interfaces for accelerated graphics port and peripheral component interconnect devices.
Sarangdhar Nitin V. (Beaverton OR) Wang Wen Han (Portland OR) Rhodehamel Michael W. (Beaverton OR) Brayton James M. (Beaverton OR) Merchant Amit (Portland OR) Fisch Matthew A. (Beaverton OR), Computer system that maintains system wide cache coherency during deferred communication transactions.
Jennings William E. (Cary NC) Chan Roland G. (Mountain View CA) Wong John L. (Belmont CA), Computer system with cascaded peripheral component interconnect (PCI) buses.
Horan Ronald Timothy ; Olarig Sompong Paul, Dual purpose apparatus, method and system for accelerated graphics port and peripheral component interconnect.
Case Colyn (Amherst NH) Meinerth Kim (Middleton MA) Irwin John (Hudson NH) Fanning Blaise (Overland Park KS), Graphics command processing method in a computer graphics system.
Carson David G. ; Hayek George R. ; Baxter Brent S. ; Case Colyn ; Meinerth Kim A. ; Langendorf Brian K., High-throughput interconnect allowing bus transactions based on partial access requests.
Watkins John (Sunnyvale CA) Labuda David (Half Moon Bay CA) Van Loo William C. (Palo Alto CA), Input/output cache with mapped pages allocated for caching direct (virtual) memory access input/output data based on typ.
Hayek George (Cameron Park CA) Oztaskin Ali S. (Beaverton OR) Langendorf Brian (El Dorado Hills CA) Young Bruce (Tigard OR), Integrated bus bridge and memory controller that enables data streaming to a shared memory of a computer system using sn.
Matsumoto John F. (Encinitas CA) Ando Motoaki (Tokyo JPX), Interface having a bus master arbitrator for arbitrating occupation and release of a common bus between a host processor.
Johnson Robert B. (Billerica MA) Nibby ; Jr. Chester M. (Peabody MA) Salas Edward R. (Billerica MA), Memory system with automatic memory configuration.
Khalidi Yousef A. (Sunnyvale CA) Nelson Michael N. (San Carlos CA), Method and apparatus for a secure protocol for virtual memory managers that use memory objects.
Milburn Blair D. (Beaverton OR) Lee Phillip G. (Aloha OR) Karnik Milind A. (Aloha OR), Method and apparatus for controlling an external cache memory wherein the cache controller is responsive to an interagen.
Ajanovic Jasmin ; Murdoch Robert N. ; Dobbins Timothy M. ; Sreenivas Aditya ; Sailer Stuart E. ; Rabe Jeffrey L., Method and apparatus for dynamically deferring transactions.
Mehring Peter A. (Wilmington MA) Becker Robert (Shirley MA) Garapetian Varoujan (Cambridge MA), Method and apparatus for increasing the speed of memory access in a virtual memory system having fast page mode.
Duke Alan H. (Pima County AZ) Hartung Michael H. (Pima County AZ) Marschner Frederick J. (Pima County AZ), Method and apparatus for managing data movements from a backing store to a caching buffer store.
Sarangdhar Nitin V. (Beaverton OR) Lai Konrad K. (Aloha OR) Singh Gurbir (Portland OR), Method and apparatus for performing bus transactions in a computer system.
Sarangdhar Nitin V. (Portland OR) Lai Konrad K. (Aloha OR) Singh Gurbir (Portland OR) MacWilliams Peter D. (Aloha OR) Pawlowski Stephen S. (Beaverton OR) Rhodehamel Michael W. (Beaverton OR), Method and apparatus for performing deferred transactions.
Lopez-Aguado Herbert (Mountain View CA) Mehring Peter A. (Sunnyvale CA), Method and apparatus for the reduction of tablewalk latencies in a translation look aside buffer.
Case Colyn (Amherst NH) Meinerth Kim (Middleton MA) Irwin John (Hudson NH) Fanning Blaise (Overland Park KS), Method and apparatus for varying command length in a computer graphics system.
Neal Danny Marvin ; Thurber Steven Mark, Method and system for supporting peripheral component interconnect (PCI) peer-to-peer access across multiple PCI host br.
Shibata Masabumi (Kawasaki JPX), Multi-processor system with lock address register in each processor for storing lock address sent to bus by another proc.
Alpert Donald B. (Santa Clara CA) Shoemaker Kenneth D. (Saratoga CA) Kahn Kevin C. (Portland OR) Lai Konrad K. (Aloha OR), Physical address size selection and page size selection in an address translator.
Weiser Uri C. (Haifa ILX) Perlmutter David (Haifa ILX) Yaari Yaakov (Haifa ILX), Pipeline system for executing predicted branch target instruction in a cycle concurrently with the execution of branch i.
Arimilli Ravi Kumar ; Dodson John Steven ; Lewis Jerry Don, Scalable symmetric multiprocessor data-processing system with data allocation among private caches and segments of syst.
Horst Robert W. ; Garcia David J. ; Bunton William Patterson ; Bruckert William F. ; Fowler Daniel L. ; Jones ; Jr. Curtis Willard ; Sonnier David Paul ; Watson William Joel ; Williams Frank A., Self-checked, lock step processor pairs.
Bodin William Kress (Boca Raton FL) Hyde David Michael (Boca Raton FL) Lay Tatchi Placido (Boca Raton FL) Wilkinson James (Southampton GBX) Yee Susan (Coral Springs FL), System for locking down part of portion of memory and updating page directory with entry corresponding to part of portio.
Kiuchi Atsushi (Kunitachi JPX) Nakagawa Tetsuya (Koganei JPX), System with loop buffer and repeat control circuit having stack for storing control information.
Hinton Glenn J. (Portland OR) Riches ; Jr. Robert M. (Hillsboro OR), Translating instruction pointer virtual addresses to physical addresses for accessing an instruction cache.
Becker Robert (Shirley MA) Mehring Peter (Wilmington MA), Translation lookaside buffer apparatus and method with input/output entries, page table entries and page table pointers.
Meinerth Kim (Middleton MA) Case Colyn (Amherst NH) Franklin Chris (Merrimack NH) Fanning Blaise (Overland Park KS) Gamache Rodney (Merrimack NH), Translation of virtual addresses in a computer graphics system.
Horan Ronald T. ; Jones Phillip M. ; Santos Gregory N. ; Lester Robert Allan ; Elliott Robert C., Valid flag for disabling allocation of accelerated graphics port memory space.
Owen Jefferson Eugene ; Diaz Raul Zegers ; Colavin Osvaldo, Video/audio decompression/compression device including an arbiter and method for accessing a shared memory.
Khalidi Yousef A. (Sunnyvale CA) Anderson Glen R. (Palo Alto CA) Chessin Stephen A. (Mountain View CA) Kong Shing I. (Menlo Park CA) Narad Charles E. (Santa Clara CA) Talluri Madhusudhan (Madison WI), Virtual address to physical address translation cache that supports multiple page sizes.
Khalidi Yousef A. (Sunnyvale CA) Talluri Madhusudhan (Madison WI) Williams Dock G. (Sunnyvale CA) Joshi Vikram P. (Fremont CA), Virtual memory computer apparatus and address translation mechanism employing hashing scheme and page frame descriptor t.
Ashmore, Paul Andrew; Davies, Ian Robert; Maine, Gene; Vedder, Rex Weldon, Certified memory-to-memory data transfer between active-active raid controllers.
Davies, Ian Robert, Safe message transfers on PCI-Express link from RAID controller to receiver-programmable window of partner RAID controller CPU memory.
※ AI-Helper는 부적절한 답변을 할 수 있습니다.