Method and apparatus for time-multiplexed processing of multiple digital video programs
View Patent ↗The present invention relates generally to the processing of multiple data streams with common resources. More particularly, this invention relates to a technique for time-multiplexed processing of, for example, multiple digital video programs. In one embodiment, an exemplary method provides for time-multiplexed processing of a set of digital streams includes storing each received packet in a random access memory. For each stream, the deadline for the arrival of the next packet at the receiver is determined and a priority based on the deadline is assigned. The stream with the highest assigned priority is identified as an identified stream. In some embodiments, the processing state of the identified stream is then restored. One or more packets of data corresponding to the identified stream are retrieved from random access memory to produce retrieved packets. The processing state is saved after the retrieved packets have been processed.
1. A method for processing a plurality of digital streams, wherein each digital stream includes packets sequenced for continuous presentation, said method comprising:
receiving packets for each of said plurality of digital streams and storing said packets in a buffer;
associating each of said packets with a respective stream of said plurality of digital streams;
assigning a priority to each packet, said priority being determined according to a delivery deadline for each of said packets;
assigning a tag to each to each packet identifying the assigned priority for the packet and an address of the packet in the buffer;
storing each tag in memory corresponding to the respective digital stream associated with each packet;
continuously monitoring the tags positioned at the memory output to identify the digital stream having the highest priority;
retrieving the packet identified by the tag at the output of the memory corresponding to the identified highest priority stream from the buffer according to said address;
determining when a new tag is present at the output of the memory after a gap in said tags for a particular one of the digital streams;
establishing the priority of the digital stream corresponding to said new tag with respect to the priority of the other digital streams; and
processing the packets from the plurality of data streams in order of priority.
2. The method of claim 1 , further comprising:
selecting said packets for processing based on said priority; and
retrieving said selected packets from said buffer.
3. The method of claim 1 , wherein:
said packets are retrieved in order of said priority.
4. The method of claim 1 , further comprising:
assigning a priority to each of said plurality of digital streams.
5. The method of claim 4 , wherein:
said assigning of said priority to each packet further comprises determining the priority of the stream associated with each packet.
6. The method of claim 1 , wherein:
said priority is based on a current time interval before said deadline.
7. The method of claim 6 , wherein:
said deadline is derived from a Decoding Time Stamp extracted from an associated packet header.
8. The method of claim 1 , wherein:
said packets of each digital stream are arranged in sequences of packets.
9. The method of claim 8 , wherein:
each sequence of packets is a representation of a video frame.
10. The method of claim 8 , wherein:
each sequence of packets is a representation of an audio frame.
11. The method of claim 1 , further comprising:
maintaining a state associated with each of said plurality of digital streams.
12. The method of claim 11 , wherein:
said state includes parameters for said processing of said packets of each stream.
13. The method of claim 11 , wherein:
said state includes pixel data representing at least one frame of video.
14. The method of claim 11 , further comprising:
allocating memory for storing said state.
15. The method of claim 14 , wherein:
said allocating memory includes recursively subdividing said memory into quadrants, where one of said quadrants cannot be further subdivided without at least one dimension becoming smaller than a corresponding dimension of a video or audio frame.
16. The method of claim 14 , wherein:
said memory is allocated in pages, where each of said pages is a contiguous memory unit of a fixed size.
17. The method of claim 16 , wherein:
unallocated pages are managed using a free list configured to manage unused pages of memory.
18. Apparatus for processing a plurality of digital streams, wherein each digital stream includes packets sequenced for continuous presentation, said apparatus comprising:
means for receiving packets for each of said plurality of digital streams and storing said packets in a buffer;
means for associating each of said packets with a respective stream of said plurality of digital streams;
means for assigning a priority to each packet, said priority being determined according to a delivery deadline for each of said packets;
means for assigning a tag to each to each packet identifying the assigned priority for the packet and an address of the packet in the buffer;
means for storing each tag in memory corresponding to the respective digital stream associated with each packet;
means for continuously monitoring the tags positioned at the memory output to identify the digital stream having the highest priority;
means for retrieving the packet identified by the tag at the output of the memory corresponding to the identified highest priority stream from the buffer according to said address;
means for determining when a new tag is present at the output of the memory after a gap in said tags for a particular one of the digital streams;
means for establishing the priority of the digital stream corresponding to said new tag with respect to the priority of the other digital streams; and
means for processing the packets from the plurality of digital streams in order of priority.
19. The apparatus of claim 18 , further comprising:
means for selecting said packets for processing based on said priority; and
means for retrieving said selected packets from said buffer.
20. The apparatus of claim 18 , further comprising:
means for assigning a priority to each of said plurality of digital streams.
21. The apparatus of claim 20 , wherein:
said priority of each packet is further determined by the priority of the stream associated with each packet.
22. The apparatus of claim 21 , further comprising:
a means for extracting a Decoding Time Stamp from an associated packet header, wherein said Decoding Time Stamp is used to derive said deadline.
23. The apparatus of claim 18 , wherein:
said priority is based on a current time interval before said deadline.
24. The apparatus of claim 18 , further comprising:
means for maintaining a state associated with each of said plurality of digital streams.
25. The apparatus of claim 24 , wherein:
said means for maintaining a state includes a memory for storing processing parameters.
26. The apparatus of claim 24 , wherein:
said means for maintaining said state includes memory for storing pixel data representing at least one frame of video.
27. The apparatus of claim 26 , further comprising:
means for recursively subdividing said memory into quadrants.
28. The apparatus of claim 26 , further comprising:
means for partitioning said memory into pages, where each of said pages is a contiguous memory unit of a fixed size.
29. The apparatus of claim 28 , further comprising:
a free list for managing unused pages of memory.
30. The apparatus of claim 28 , further comprising:
a translation look-aside buffer for mapping virtual addresses to physical page addresses.
31. The apparatus of claim 28 , further comprising:
means for retrieving pages from memory and merging data into blocks of a requested size.
32. The apparatus of claim 31 , further comprising:
a cache for storing one or more pages that have been retrieved from memory.