Tree-coded video compression with coupled pipelines

1. An apparatus comprising:

a circuit configured to (i) generate a plurality of sets of coefficients by compressing a tile in a picture in a video signal at each of a plurality of different sizes of a plurality of coding units in a coding tree unit and (ii) generate an output signal by entropy encoding a particular one of said sets of coefficients, wherein (a) said sets of coefficients are generated at two or more of said different sizes of said coding units in parallel, (b) each of said sets of coefficients is generated in a corresponding one of a plurality of pipelines that operate in parallel, (c) each of said sets of coefficients has a same number of said coefficients and (d) each of said sets of coefficients represents said tile with a different number of said coding units; and

a processor configured to select said particular set of coefficients in response to said compression of said tile.

2. The apparatus according to claim 1 , wherein said circuit is further configured to load a reference picture in parallel from a shared portion of said pipelines into separate ones of said pipelines.

3. The apparatus according to claim 1 , wherein each one of said pipelines compresses said tile at a respective one of said different sizes of said coding units in parallel.

4. The apparatus according to claim 1 , wherein each one of said pipelines finishes said compression of said tile at said different sizes of said coding units at approximately a same time.

5. The apparatus according to claim 1 , wherein (i) a first of said pipelines compresses said tile at said two or more of said different sizes of said coding units in a time multiplexed sequence and (ii) said first pipeline finishes said compression of said tile at said two or more different sizes of said coding units and a second of said pipelines finishes said compression of said tile at another of said different sizes of said coding units at approximately a same time.

6. The apparatus according to claim 1 , where said pipelines have a common stage.

7. The apparatus according to claim 1 , wherein each one of said pipelines interleaves compression of said tile with compression of another tile in said picture.

8. The apparatus according to claim 1 , wherein said output signal is compliant with an International Telecommunication Union-Telecommunications Recommendation H.265.

9. The apparatus according to claim 1 , wherein each of said pipelines has a number of unique stages that is prime with respect to a tree branching factor.

10. A method for tree-coded video compression with coupled pipelines, comprising the steps of:

generating a plurality of sets of coefficients by compressing a tile in a picture in a video signal at each of a plurality of different sizes of a plurality of coding units in a coding tree unit, wherein (i) said sets of coefficients are generated at two or more of said different sizes of said coding units in parallel, (ii) each of said sets of coefficients is generated in a corresponding one of a plurality of said pipelines that operate in parallel, (iii) each of said sets of coefficients has a same number of said coefficients and (iv) each of said sets of coefficients represents said tile with a different number of said coding units;

selecting a particular one of said sets of coefficients in response to said compression of said tile; and

generating an output signal by entropy encoding said particular set of coefficients.

11. The method according to claim 10 , further comprising the step of:

loading a reference picture in parallel from a shared portion of said pipelines into separate ones of said pipelines.

12. The method according to claim 10 , wherein each one of said pipelines compresses said tile at a respective one of said different sizes of said coding units in parallel.

13. The method according to claim 10 , wherein each one of said pipelines finishes said compression of said tile at said different sizes of said coding units at approximately a same time.

14. The method according to claim 10 , wherein (i) a first of said pipelines compresses said tile at said two or more of said different sizes of said coding units in a time multiplexed sequence and (ii) said first pipeline finishes said compression of said tile at said two or more different sizes of said coding units and a second of said pipelines finishes said compression of said tile at another of said different sizes of said coding units at approximately a same time.

15. The method according to claim 10 , where said pipelines have a common stage.

16. The method according to claim 10 , wherein each one of said pipelines interleaves compression of said tile with compression of another tile in said picture.

17. The method according to claim 10 , wherein each of said pipelines has a number of unique stages that is prime with respect to a tree branching factor.

18. An apparatus comprising:

means for generating a plurality of sets of coefficients by compressing a tile in a picture in a video signal at each of a plurality of different sizes of a plurality of coding units in a coding tree unit, wherein (i) said sets of coefficients are generated at two or more of said different sizes of said coding units in parallel, (ii) each of said sets of coefficients is generated in a corresponding one of a plurality of pipelines that operate in parallel, (iii) each of said sets of coefficients has a same number of said coefficients and (iv) each of said sets of coefficients represents said tile with a different number of said coding units;

means for selecting a particular one of said sets of coefficients in response to said compression of said tile; and

means for generating an output signal by entropy encoding said particular set of coefficients.