Optimal Power Usage in Encoding Data Streams

• US 20100128777A1
• Filed: 11/24/2008
• Published: 05/27/2010
• Est. Priority Date: 11/24/2008
• Status: Active Grant

• Current Assignee: NVIDIA Corporation
• Original Assignee: NVIDIA Corporation
• Inventors: Pandey, Manish Jatashanker, Reddy, Harikrishna Madadi, Pore, Vinayak Jayaram, Parhy, Manindra Nath, Dey, Soumenkumar, Garg, Shashank
• Granted Patent: US 8,442,111 B2
• Time in Patent Office: Days
• US Class Current: 375/240.10
• CPC Class Codes: H04N 19/107 between spatial and temporal predictive coding, e.g. picture refresh
• CPC Class Codes: H04N 19/132 Sampling, masking or truncation of coding units, e.g. adaptive resampling, frame skipping, frame interpolation or high-frequency transform coefficient masking
• CPC Class Codes: H04N 19/156 Availability of hardware or computational resources, e.g. encoding based on power-saving criteria
• CPC Class Codes: H04N 19/172 the region being a picture, frame or field
• CPC Class Codes: H04N 19/42 characterised by implementation details or hardware specially adapted for video compression or decompression, e.g. dedicated software implementation H04N19/635 takes precedence
• CPC Class Codes: H04N 19/523 with sub-pixel accuracy
• CPC Class Codes: H04N 19/587 involving temporal sub-sampling or interpolation, e.g. decimation or subsequent interpolation of pictures in a video sequence

Abstract

An encoder provided according to an aspect of the present invention uses different encoding techniques depending on an amount of power available in the corresponding durations. Due to the ability to use such different encoding techniques, power may be optimally utilized. The optimization is further enhanced by dynamically switching between encoding techniques according to power amount availability in corresponding durations. In an embodiment, each encoding technique estimates motion vectors at corresponding level of precision (thereby consuming a corresponding level of power) and the precision level is chosen to correspond to available power budget. The circuitry not required for a desired precision level may be switched off.

Claims

1. A device comprising:

an encoder to encode a data stream; and

a power management module to indicate an amount of available power,

wherein said encoder is designed to encode said data stream using a first encoding technique if said amount is above a threshold and to encode using a second encoding technique otherwise.

2. The device of claim 1, wherein said power management module is designed to indicate a sequence of amounts of available power at corresponding time instances,

wherein said data stream comprises a sequence of digital values,

wherein said encoder selects said first encoding technique or said second encoding technique in response to receiving each of said sequence of amounts and encodes a corresponding subset of said sequence of digital value according to the selected encoding technique.

3. The device of claim 2, wherein said first encoding technique requires more power than said second encoding technique to encode a same amount of digital values, whereby encoding technique requiring more power is selected when said amount of available power is more.

4. The device of claim 3, wherein said encoder comprises a first block and a second block which respectively perform said first encoding technique and said second encoding technique, wherein said first block is operable to be switched off when said second encoding technique is selected and is operable to be switched on when said first encoding technique is selected.

5. The device of claim 4, wherein said sequence of digital values represent a sequence of image frames, wherein said first block is designed to estimate motion between successive image frames at a first resolution and said second block is designed to estimate motion between successive image frames at a second resolution, wherein said first resolution is more than said second resolution.

6. The device of claim 5, wherein said first resolution is equal to a fraction of a pixel of the image frames and said second resolution equals one pixel of the image frames.

7. The device of claim 6, further comprising a software driver to receive said amount of available power, to select said first encoding technique or said second encoding technique, and to switch off one of said first block and said second block.

8. The device of claim 7, further comprising a central processing unit (CPU) and a memory, said power management module to compute said amount of available power based on a power received from a power supply and power requirements of said CPU and said memory.

9. The device of claim 7, wherein said second encoding technique further comprising;

dropping the intermediate image frames; and

adjusting a rate control parameter to provide output at a desired bit rate.

10. An encoder to encode a sequence of digital values, said encoder comprising:

a first block to perform an encoding operation based on a first encoding technique;

a second block to perform said encoding operation based on a second encoding technique; and

a driver to receive an amount of available power, and to determine to encode said data stream using said first encoding technique if said amount is above a threshold and to encode using said second encoding technique otherwise,

said driver to switch off said first block if said sequence of digital values are to be encoded using said second encoding technique and to switch off said second block if said sequence of digital values are to be encoded using said first encoding technique.

11. The encoder of claim 10, wherein said driver is designed to receive a sequence of amounts of available power at corresponding time instances,

wherein said data stream comprises said sequence of digital values,

wherein said driver selects said first encoding technique or said second encoding technique in response to receiving each of said sequence of amounts and causes encoding of a corresponding subset of said sequence of digital value according to the selected encoding technique.

12. The encoder of claim 11, wherein said first encoding technique requires more power than said second encoding technique to encode a same amount of digital values, whereby encoding technique requiring more power is selected when said amount of available power is more.

13. The encoder of claim 12, wherein said sequence of digital values represent a sequence of image frames, wherein said first block is designed to estimate motion between successive image frames at a first resolution and said second block is designed to estimate motion between successive image frames at a second resolution, wherein said first resolution is more than said second resolution.

14. The encoder of claim 13, wherein said first resolution is equal to a fraction of a pixel of the image frames and said second resolution equals one pixel of the image frames.

15. The encoder of claim 14, wherein said image frames are encoded according to H.264 standard.

16. A method of processing a digital data stream, said method comprising:

receiving an indication of an amount of available power;

selecting a first encoding technique if said amount is above a threshold and a second encoding technique otherwise; and

encoding said digital bit stream according to said selected encoding technique.

17. The method of claim 16, wherein said receiving step receives a sequence of amounts of available power at corresponding time instances,

wherein said data stream comprises a sequence of digital values,

wherein said selecting step selects said first encoding technique or said second encoding technique in response to receiving each of said sequence of amounts, and

said encoding step encodes a corresponding subset of said sequence of digital value according to each of the selected encoding techniques.

18. The method of claim 17, wherein said first encoding technique requires more power than said second encoding technique to encode a same amount of digital values, whereby said selecting step encodes a technique requiring more power when said amount of available power is more.

19. The method of claim 18, wherein an operation of said encoding is performed using a plurality of components, said method further comprises swithcing on or off some of said plurality of components.

20. The method of claim 19, wherein each of said plurality of components is designed to perform motion estimation at a corresponding precision.