1. 29 Sep, 2017 1 commit
  2. 28 Sep, 2017 1 commit
  3. 27 Sep, 2017 2 commits
  4. 22 Sep, 2017 1 commit
  5. 20 Sep, 2017 3 commits
  6. 19 Sep, 2017 2 commits
  7. 12 Sep, 2017 1 commit
    • Johann's avatar
      Revert "Revert "quantize avx: copy 32x32 implementation"" · eb4238ac
      Johann authored
      This reverts commit 8c42237b.
      
      Because ssse3 code is used for the reference, the qcoeff and dqcoeff
      reference buffers must be aligned.
      
      Original change's description:
      > quantize avx: copy 32x32 implementation
      >
      > Ensure avx and ssse3 stay in sync by testing them against each other.
      >
      > Change-Id: I699f3b48785c83260825402d7826231f475f697c
      
      Change-Id: Ieeef11b9406964194028b0d81d84bcb63296ae06
      eb4238ac
  8. 11 Sep, 2017 1 commit
  9. 07 Sep, 2017 1 commit
  10. 05 Sep, 2017 2 commits
  11. 30 Aug, 2017 1 commit
  12. 29 Aug, 2017 2 commits
  13. 25 Aug, 2017 1 commit
    • Marco Paniconi's avatar
      Revert "quantize avx: copy 32x32 implementation" · 8c42237b
      Marco Paniconi authored
      This reverts commit f60d1dcd.
      
      Reason for revert: <INSERT REASONING HERE>
      Failures in AVX/VP9QuantizeTest in nightly tests.
      Original change's description:
      > quantize avx: copy 32x32 implementation
      > 
      > Ensure avx and ssse3 stay in sync by testing them against each other.
      > 
      > Change-Id: I699f3b48785c83260825402d7826231f475f697c
      
      TBR=slavarnway@google.com,johannkoenig@google.com,builds@webmproject.org
      
      Change-Id: Ibd38636212269328317dd0721be9d25452113d1c
      No-Presubmit: true
      No-Tree-Checks: true
      No-Try: true
      8c42237b
  14. 24 Aug, 2017 2 commits
  15. 23 Aug, 2017 1 commit
    • Johann's avatar
      quantize avx: copy implementation to intrinsics · 7c278721
      Johann authored
      Adds an early exit based on ptest. Slightly slower than ssse3 in the
      full case because of the extra check, but potentially faster if lots of
      rows can be skipped.
      
      Very close in speed to the assembly.
      
      Can run in 32 bit, unlike the assembly. Allows reworking the function
      prototype to use structs.
      
      Change-Id: If80e2b9ba059370a4cad3c973196e82a97b4330e
      7c278721
  16. 22 Aug, 2017 2 commits
  17. 21 Aug, 2017 1 commit
  18. 18 Aug, 2017 2 commits
  19. 17 Aug, 2017 2 commits
  20. 15 Aug, 2017 1 commit
  21. 14 Aug, 2017 2 commits
  22. 09 Aug, 2017 1 commit
  23. 08 Aug, 2017 2 commits
    • Johann's avatar
      quantize: copy ssse3 optimizations to intrinsics · d52cb597
      Johann authored
      Fairly minor differences from sse2. pabsw and psignw are the big gains.
      Also re-uses some values in eob calculation to avoid an extra pcmp.
      
      Fixes test failures in HBD and OS X builds.
      
      Allows using it in 32bit builds, where it is about 40% faster than sse2.
      
      Substantially faster than the assembly for skip_block. 10-20% faster the
      rest of the time.
      
      Change-Id: If783bb3567e561e47667e10133b9c84414a334e2
      d52cb597
    • Linfeng Zhang's avatar
      Update 32x32 idct sse2 funcs, add partial case 135 · 853165ba
      Linfeng Zhang authored
      Change-Id: I2b9add83f6fd8f9138fed3bec04a59877a237a6a
      853165ba
  24. 04 Aug, 2017 5 commits