Processor with decompressed video bus

• US 6,219,754 B1
• Filed: 12/19/1997
• Issued: 04/17/2001
• Est. Priority Date: 06/07/1995
• Status: Expired due to Term

• Current Assignee: Advanced Micro Devices, Inc.
• Original Assignee: Advanced Micro Devices, Inc.
• Inventors: Dutton, Drew J., Stewart, Brett B., Belt, Steven L., Gephardt, Douglas D., Wisor, Rita M.
• Primary Examiner(s): Thai, Tuan V.
• Application Number:
  US08/994,489
• Time in Patent Office: 1,215 Days
• Field of Search: 345/144, 710/113, 710/58, 710/128, 358/263, 382/166, 711/100, 711/118
• US Class Current: 711/118
• CPC Class Codes: G06F 12/0875 with dedicated cache, e.g. instruction or stack

Abstract

A dedicated bus between a central processing unit and a peripheral unit, such as a graphics controller driving a video display, provides enhanced capability in an environment in which signal processing occurs within the central processing unit. The dedicated bus relieves other data buses, such as the PCI bus, of the need to communicate large amounts of data, such as decompressed video data. The resulting system supports high bandwidth transmissions of decompressed video data, enabling high resolution 24 bit full motion video and multiple data stream video.

Claims

1. A data processing system, comprising:

a central processing unit receiving compressed video data from a video source via a PCI bus and producing decompressed video data therefrom; and

a graphics controller receiving the decompressed video data from the central processing unit via a dedicated bus, said dedicated bus being different from said PCI bus and being exclusively dedicated to data transfer between said graphics controller and said central processing unit;

a bridge connected to said PCI bus;

a memory controller connected to said bridge; and

an L2 cache memory connected between said memory controller and said central processing unit;

wherein the compressed video data is supplied to said central processing unit via said bridge, said memory controller and said L2 cache memory from said PCI bus;

wherein the dedicated bus is separate from the PCI bus;

wherein the dedicated bus is not connected in any way to the PCI bus; and

wherein the data transfer of the decompressed video data between said graphics controller and said central processing unit is only through the dedicated bus and not through any part of the PCI bus.

2. A data processing system as recited in claim 1, wherein the central processing unit includes a digital signal processor, the digital signal processor of the central processing unit producing the decompressed video data from the compressed video data.

3. A data processing system as recited in claim 1, wherein the central processing unit is configured such that the central processing unit processes the compressed video data into decompressed video data according to a software program.

4. A data processing system as recited in claim 1, further comprising a display connected to the graphics controller, the display displaying video images corresponding to the decompressed video data under the control of the graphics controller.

5. A data processing system comprising:

a central processing unit for receiving compressed video data from a video source and producing decompressed video data therefrom;

a memory;

a first bus having a plurality of devices communicatively connected thereto to provide information to each other and said central processing unit;

a graphics controller and a second bus, said second bus providing a point-to-point connection for dedicated communication between said central processing unit and said graphics controller;

a bridge connected to said first bus;

a memory controller connected to said bridge; and

an L2 cache memory connected between said memory controller and said central processing unit;

wherein the compressed video data is supplied to said central processing unit via said bridge, said memory controller and said L2 cache memory from said first bus;

wherein said graphics controller is not connected to said first bus and said second bus is exclusively dedicated to data transfer between said graphics controller and said central processing unit; and

wherein the data transfer between said graphics controller and said central processing unit is only through said second bus and not through any part of said first bus.

6. The apparatus recited in claim 5, wherein said central processing unit controls access to said second bus.

7. The apparatus recited in claim 6, wherein said central processing unit stores a program to recognize address ranges in said memory and provide information to said second bus when said address ranges are accessed.

8. The apparatus recited in claim 7, wherein said address ranges are stored as predetermined ranges.

9. The apparatus recited in claim 7, wherein said address ranges are stored as dynamically allocated ranges.

10. The apparatus recited in claim 9, wherein said dynamically allocated ranges are determined by system requirements.

11. The apparatus recited in claim 6, wherein said central processing unit is responsive to a field of an instruction to elect one of said first bus and said second bus.

12. The apparatus recited in claim 6, further comprising a direct memory access buffer.

13. The apparatus recited in claim 12, wherein said direct memory access buffer is responsive to commands from said CPU to transfer data from said memory to said second bus.

14. The apparatus recited in claim 6, wherein said central processing unit comprises a dedicated CPU engine responsive to predetermined commands to access said second bus.

15. The apparatus recited in claim 5, wherein said second bus provides bit block transfers between said graphics controller and said central processing unit.

16. The apparatus recited in claim 5, further comprising a video frame buffer, said video frame buffer receiving a video frame built in said memory and transmitting said video frame to said second bus.

17. The apparatus as recited in claim 5, wherein said second bus is a bi-directional bus.

18. The apparatus as recited in claim 17, wherein said second bus comprises a data streaming bus.

19. The apparatus as recited in claim 5, wherein said second bus is linked to a custom interface for said graphics controller.

20. A method of processing data, comprising the steps of:

receiving compressed video data in a central processing unit via a PCI bus;

decompressing the compressed video data in the central processing unit to produce decompressed video data; and

supplying the decompressed video data from the central processing unit to a graphics controller via a second, dedicated bus, said dedicated bus being exclusively dedicated to data transfer between said graphics controller and said central processing unit;

providing a bridge connected to said PCI bus;

providing a memory controller connected to said bridge;

providing an L2 cache memory connected between said memory controller and said central processing unit;

wherein the compressed video data is supplied to said central processing unit via said bridge, said memory controller and said L2 cache memory from said PCI bus;

wherein the data transfer of the decompressed video data between said graphics controller and said central processing unit is only through the dedicated bus and not through any part of the PCI bus.

21. The method recited in claim 20, further comprising the step of displaying, on a display, video images corresponding to the decompressed video data.

22. The method recited in claim 20, wherein said central processing unit controls access to said second bus.

23. The method recited in claim 20, wherein said central processing unit stores a program to recognize address ranges in a memory and provide information to said second bus when said address ranges are accessed.

24. The method recited in claim 23, wherein said address ranges are stored as predetermined ranges.

25. The method recited in claim 23, wherein said address ranges are stored as dynamically allocated ranges.

26. The method recited in claim 25, wherein said dynamically allocated ranges are determined by system requirements.

27. The method recited in claim 20, wherein said central processing unit is responsive to a field of an instruction to elect one of said first bus and said second bus.

28. The method recited in claim 20, wherein a direct memory access buffer is responsive to commands from said CPU to transfer data from said memory to said second bus.

29. The method recited in claim 20, wherein said central processing unit comprises a dedicated CPU engine responsive to predetermined commands to access said second bus.