1. 30 Aug, 2016 2 commits
  2. 29 Aug, 2016 1 commit
  3. 19 Aug, 2016 1 commit
  4. 18 Aug, 2016 1 commit
  5. 19 Jul, 2016 1 commit
  6. 07 Jul, 2016 1 commit
    • Cedric Roux's avatar
      hotfix: remove HARQ process ID freelist · 69ec9112
      Cedric Roux authored
      It creates more problems than it solves.
      
      We replace this approach by a straightforward
      synchronous one.
      
      Now in the downlink, at frame f and subframe s
      we use HARQ process (f * 10 + s) % 8.
      This is similar to uplink scheduling.
      69ec9112
  7. 20 Jun, 2016 1 commit
  8. 16 Jun, 2016 1 commit
  9. 10 Jun, 2016 1 commit
  10. 09 Jun, 2016 1 commit
  11. 06 Jun, 2016 2 commits
  12. 02 Jun, 2016 1 commit
  13. 11 May, 2016 1 commit
  14. 22 Apr, 2016 1 commit
  15. 10 Apr, 2016 2 commits
  16. 06 Apr, 2016 1 commit
  17. 01 Apr, 2016 1 commit
  18. 27 Mar, 2016 2 commits
  19. 20 Mar, 2016 1 commit
  20. 15 Mar, 2016 1 commit
  21. 13 Mar, 2016 1 commit
  22. 02 Mar, 2016 1 commit
  23. 25 Feb, 2016 1 commit
  24. 19 Feb, 2016 2 commits
  25. 11 Feb, 2016 2 commits
  26. 09 Feb, 2016 1 commit
  27. 04 Feb, 2016 1 commit
  28. 03 Feb, 2016 1 commit
  29. 01 Feb, 2016 2 commits
  30. 23 Jan, 2016 1 commit
  31. 07 Jan, 2016 1 commit
  32. 06 Jan, 2016 1 commit
  33. 03 Jan, 2016 1 commit
    • knopp's avatar
      added avx2 optimized turbo decoder for 16-bit LLR. This decoder parallelizes... · 8d4405bd
      knopp authored
      added avx2 optimized turbo decoder for 16-bit LLR.  This decoder parallelizes by decoding 2 code segments concurrently. requires updates dlsch_decoding.c to identify when new parallel version can be used. other minor changes related to memory allocations for future avx2 optimizations (32-byte alignment).
      8d4405bd