Method and apparatus for decoding data
View Patent ↗Decoding an encoded block of data is accomplished by partitioning the block into a first and a second sub-block and performing forward and backward iterative calculations on the sub-blocks in separate processes. Based on results of the iterative calculations an output matrix may be calculated for each sub-block. The outputs may be combined.
1. A method of decoding an encoded block of data comprising:
partitioning the block into a first and a second sub-block assigned to a first and second process respectively; and
performing backward iterative calculations on the first sub-block within some point of a second portion of the second sub-block based on results from backward iterative calculations on a first portion of the second sub-block.
2. The method according to claim 1 , further comprising:
performing forward iterative calculations on the first sub-block.
3. The method according to claim 2 , further comprising: calculating a first output based on the results of the forward and backward iterative calculations performed on the first sub-block.
4. The method according to claim 3 , further comprising:
performing forward and backward iterative calculations on the second sub-block and calculating a second output based on the results of the forward and backward iterative calculations on the second block.
5. The method according to claim 4 , further comprising:
combining the first and second outputs into a single data black.
6. The method according to claim 4 , further comprising:
storing the results of the iterative calculation of the second sub-block on a temporary memory on which results from the iterative calculation of the first sub-block are stored.
7. The method according to claim 6 , wherein results from the iterative calculations on the second sub-block are stored to a portion of the temporary memory after an output based on results stored in that portion of memory is calculated.
8. A decoder comprising:
a processing unit to start to perform a backward iterative calculation on a first sub-block within some point of a second portion of the second sub-block, based on results of a backward iterative calculation performed by a second processing unit on a first portion of a second sub-block.
9. The decoder according to claim 8 , wherein said processing unit is adapted to perform forward iterative calculations on the first sub-block.
10. The decoder according to claim 9 , wherein said processing unit is adapted to calculate an output for the first sub-block based on the forward and backward iterative calculations for the sub-block.
11. The decoder according to claim 10 , wherein said second processing unit is to perform backward and forward iterative calculations of the second sub-block and to calculate an output for the second sub-block based on results from the forward and backward calculations on the second sub-block.
12. The decoder according to claim 11 , wherein the processing unit comprises:
a forward iterative calculator, a backward iterative calculator and an output calculator.
13. The decoder according to claim 12 , further comprising:
a temporary memory.
14. The decoder according to claim 13 , wherein said temporary memory is configured to store the results of iterative calculations on a first sub-block and then the results of iterative calculations on a second sub-block.
15. The decoder according to claim 14 , wherein portions of said temporary memory are freed up as an output of the first sub-block is calculated.
16. The decoder according to claim 15 , wherein results from iterative calculations on the second sub-block are stored in the freed portion of said temporary memory.
17. An apparatus comprising:
a data block parser to parse an encoded data block into at least first and second sub-blocks;
at least first and second processing units to perform forward and backward decoding at least on the first and second sub-blocks, respectively, of the encoded data block wherein, the backward decoding of the first sub-block is able to start within iterative calculations of the second sub-black; and
a memory to store outputs of at least the first and second processing units.
18. The apparatus of claim 17 , wherein the first processing unit is able to perform a backward iterative calculation on at least a portion of the first sub-block based on results of a backward iterative calculation performed by the second processing unit on at least a portion of the second sub-block.
19. The apparatus of claim 18 , wherein the first processing unit is able to perform forward iterative calculations on at least a portion of the first sub-block.
20. The apparatus of claim 19 , wherein the first processing unit is able to decode the first sub-block and to provide an output based on the forward and backward iterative calculations preformed on the first sub-block.
21. The apparatus of claim 18 , wherein the second processing unit is able to perform backward and forward iterative calculations of the second sub-block and to provide an output based on results from the forward and backward calculations preformed on the second sub-block.
22. The apparatus of claim 17 , wherein the memory is able to store the results of the iterative calculations preformed on the first sub-block and the results of the iterative calculations preformed on the second sub-block.
23. The apparatus of claim 22 , wherein portions of the memory are freed up as an output of the first sub-block is calculated.
24. The apparatus of claim 23 , wherein results output from iterative calculations on the second sub-block are stored in the freed up portions of the memory.
25 .The apparatus of claim 17 , wherein the first and second sub-blocks are partitioned into two or more sub-block segments.
26. The apparatus of claim 25 , wherein at least some of the sub-block segments are decoded by a separate thread and/or separate process running on one of the processing unit.
27. The apparatus of claim 25 , wherein at least some of the sub-block segments are decoded by a separate thread and/or separate process running on a digital signal processor.
28. A method comprising:
parsing an encoded data block into first and second sub-blocks; and
performing a forward and backward decoding on the first and second sub-blocks by decoders of first and second processing units wherein, the backward decoding of the first sub-block is able to start within iterative calculations of a portion of the second sub-block.
29. The method of claim 28 , further comprising:
performing a backward iterative calculation an the first sub-block based on results of a backward iterative calculation performed on at least a portion of the second sub-block.
30. The method of claim 28 , wherein performing a forward and backward decoding on the first and second sub-blocks comprises decoding sub-block segments by a separate thread and/or separate process.
31. The method of claim 28 , further comprising:
storing the results output from iterative calculations on a first sub-block and the results output from iterative calculations on a second block.
32. The method of claim 31 , wherein storing comprises:
freeing up portions of a memory as an output of the first sub-block is calculated; and
storing results output from iterative calculations on the second sub-block in the freed up portion of the memory.