System and technique for reducing power consumed by a data transfer operations during periods of update inactivity

• US 5,961,617 A
• Filed: 08/18/1997
• Issued: 10/05/1999
• Est. Priority Date: 08/18/1997
• Status: Expired due to Term

• Current Assignee: St Clair Intellectual Property Consultants Incorporated
• Original Assignee: Vadem Limited
• Inventors: Tsang, Siu Keun
• Primary Examiner(s): Ray, Gopal C.
• Application Number:
  US08/914,846
• Time in Patent Office: 778 Days
• Field of Search: 395/750.01, 395/750.03, 395/750.05, 345/202, 712/300, 712/320, 712/323, 710/1, 710/18, 710/100, 711/100, 282/233, 340/825.06
• US Class Current: 710/100
• CPC Class Codes: G06F 1/3218 of display devices
• CPC Class Codes: G09G 2310/04 Partial updating of the display screen
• CPC Class Codes: G09G 2320/103 Detection of image changes, e.g. determination of an index representative of the image change
• CPC Class Codes: G09G 2330/021 Power management, e.g. power saving
• CPC Class Codes: G09G 2330/022 in absence of operation, e.g. no data being entered during a predetermined time
• CPC Class Codes: G09G 2340/02 Handling of images in compressed format, e.g. JPEG, MPEG
• CPC Class Codes: G09G 2350/00 Solving problems of bandwidth in display systems
• CPC Class Codes: G09G 5/39 Control of the bit-mapped memory

Abstract

A system and method are described that reduce display subsystem power consumption in computer systems where image data is transferred from an image memory to a display each time a new image frame is displayed. In normal operation, the computer system displays uncompressed image data, which is stored in the image memory. After a period of display inactivity, a display processor compresses the uncompressed data and writes the compressed data to another location in the image memory. In subsequent display cycles, until there is display activity, the display processor retrieves the compressed data from the memory, decompresses it in real time and then transfers the decompressed data to the display. Entire images or segments of images can be compressed in this manner. Using the compressed image data saves display power as it requires fewer memory cycles to transfer from the memory to the display than the uncompressed data. Bus bandwidth available for other, unrelated activities increases as the result of this bandwidth reduction, which benefits other system operations.

Claims

1. A data interface system, comprising:

a processing unit configured to receive input data from a memory and generate from the received input data corresponding output data;

an uncompressed version of the input data, which is stored in the memory; and

a compressed version of the input data, which is stored in the memory;

such that;

the processing unit is configured, when the input data has not been recently updated, to generate the compressed version from the uncompressed version and to generate the output data from the compressed version; and

the processing unit is configured, when the input data has been recently updated, to use at least a subset of the uncompressed version to generate the output data.

2. The system of claim 1, further comprising:

an activity monitor configured to determine whether the input data has been recently updated and to communicate the determination to the processing/control unit, which uses the determination to generate the output data from an appropriate combination of the input data versions.

3. The system of claim 1, wherein, when any part of the input data is updated, the processing unit is configured to generate the output data using the uncompressed version in its entirety.

4. The system of claim 1, wherein the compressed version is structured so that distinct regions of the input data are represented in the compressed version by respective compressed regions;

such that, when one or more of the distinct regions are updated, the processing unit is configured to generate the output data using the uncompressed regions that correspond to the updated distinct regions and the compressed regions that correspond to the distinct regions that were not updated.

5. The system of claim 1, wherein the input data is transferred between the memory and the processing unit over a bus.

6. The system of claim 1, wherein transferring the uncompressed version instead of the compressed version frees up additional memory bus bandwidth for unrelated system operations.

7. The system of claim 6, wherein transferring the compressed version over a bus dissipates less power than transferring the uncompressed version over the bus.

8. The system of claim 7, wherein the processing unit, memory and bus are deployed within a computer system with limited power reserves.

9. The system of claim 8, wherein the computer system comprises a handheld device, a portable device, a battery-power device, or any other device that utilizes/demands a continuous and sometimes repetitive incoming data stream.

10. The system of claim 1, wherein the input data is display/video data, the processing unit performs text/graphical/video display operations and the output data is text/graphics/video data.

11. The system of claim 10, further comprising:

an activity monitor configured to determine whether the display/video data has been recently updated and to communicate the determination to the processing unit, which uses the determination to generate the text/graphics/video data from an appropriate set of the input data versions.

12. The system of claim 10;

wherein, when any part of the display video data is updated, the processing unit is configured to generate the text/graphics/video data using the uncompressed version in its entirety.

13. The system of claim 10, wherein the compressed and uncompressed versions are structured so that one or more parts of the display/video data corresponding to respective groups of contiguous text/graphics/video data are represented in the versions by corresponding data regions;

such that the processing unit is configured to generate the text/graphics/video data using uncompressed regions corresponding to updated parts of the display/video data and compressed regions corresponding to un-updated regions of the display/video data.

14. The system of claim 10, wherein the compressed version is compressed using a compression method selected from a plurality of methods including at least one of the following:

run length encoding (RLE);

JPEG (joint photographic experts croup); and

MPEG (motion picture experts group).

15. The system of claim 1, wherein the input data is any type of data that must be transferred repeatedly and continuously by the processing unit to and from a second processing unit.

16. The system of claim 1, further comprising:

a hardware compression and decompression engine configured to improve power savings and enhance performance of the system by assisting the processing unit to generate the compressed version by compressing the uncompressed version and to generate the output data by decompressing the compressed version.

17. A data interface method, comprising the steps of:

receiving input data from a memory;

determining whether the input data has been recently updated;

generating, when at least a subset of the input data has not been recently updated, a compressed version of the subset of the input data; and

generating, as long as the subset is not subsequently updated, corresponding output data from the compressed version of the subset.

18. The method of claim 17, further comprising the step of:

generating output data for regions of the input data which have been recently updated from corresponding uncompressed input data.

19. The method of claim 18, further comprising the step of storing the compressed version in the memory for use in subsequent display operations;

wherein the receiving step comprises;

receiving the compressed version for the subset not recently updated; and

receiving the uncompressed input data for the regions recently updated.

20. The method of claim 19, wherein the input data is received over a bus.

21. The method of claim 20, wherein receiving the input data formed as a combination of the compressed version and the uncompressed version frees up additional memory bus bandwidth for unrelated system operations.

22. The method of claim 19, wherein receiving the compressed version over a bus dissipates less power than receiving the corresponding subset of the uncompressed input data.

23. The method of claim 17, further comprising the steps of:

discontinuing the step of generating the compressed version when the size of the compressed version exceeds a predetermined percentage of the size of the subset of the input data and instead generating the corresponding output data from the subset of the input data.

24. The method of claim 17, wherein, when the subset of the input data not recently updated comprises less than 100% of the input data;

the output data generating step comprises generating the output data directly from the input data.

25. The method of claim 17, wherein the compressed version is structured so that distinct regions of the input data are represented in the compressed version by respective compressed regions;

such that, when one or more of the distinct regions are updated, the output data is generated using the uncompressed regions that correspond to the updated distinct regions and the compressed regions that correspond to the distinct regions that were not updated.

26. The method of claim 17, wherein the input data is display/video data and the output data is text/graphics/video data.

27. The method of claim 26, wherein, when the subset of the display/video data not recently updated comprises less than 100% of the display/video data;

the output data generating step comprises generating the text/graphics/video data directly from the display/video data.

28. The method of claim 26, wherein the compressed version is structured so that distinct regions of the display/video data are represented in the compressed version by respective compressed regions;

such that, when one or more of the distinct regions are updated, the text/graphics/video data is generated using the uncompressed regions that correspond to the updated distinct regions and the compressed regions that correspond to the distinct regions that were not updated.

29. The method of claim 26, wherein the compressing step comprises compressing the input data using a compression method selected from a plurality of methods including at least one of the following:

run length encoding (RLE);

JPEG (joint photographic experts group); and

MPEG (motion picture experts group).

30. The method of claim 17, wherein the input data is any type of data that must be transferred repeatedly and continuously by a display processor to and from a second processing unit.

31. The method of claim 17,

wherein:

the step of generating the compressed version includes compressing in hardware the subset of the input data; and

the step of generating the output data includes decompressing in hardware the compressed version of the subset.