Skip to content
GitLab
  1. 27 Aug, 2016 1 commit
  3. 28 Jun, 2016 1 commit
  5. 08 Jun, 2016 1 commit
    • Linfeng Zhang's avatar
      remove mmx variance functions (from libvpx) · 7056e3a0
      Linfeng Zhang authored and James Zern's avatar James Zern committed 
      Cherry-pick d0ffae82 remove mmx variance functions

there are sse2 equivalents which is a reasonable modern baseline
Removed mmx variance functions:
vpx_get_mb_ss_mmx()
vpx_get8x8var_mmx()
vpx_get4x4var_mmx()
vpx_variance4x4_mmx()
vpx_variance8x8_mmx()
vpx_mse16x16_mmx()
vpx_variance16x16_mmx()
vpx_variance16x8_mmx()
vpx_variance8x16_mmx()

Change-Id: Ife4e67fe85e0012ca560a98831f69195c852a645
      7056e3a0
  7. 03 May, 2016 1 commit
  9. 29 Mar, 2016 2 commits
  11. 28 Mar, 2016 1 commit
  13. 25 Mar, 2016 3 commits
  15. 22 Mar, 2016 2 commits
    • Yaowu Xu's avatar
      libvpx -> libaom · 3d26d916
      Yaowu Xu authored 
      Change-Id: I820483aefdc14f2ae946e08fe10fa01f3e845767
      3d26d916
    • Yaowu Xu's avatar
      Rename vpx to aom · bf4202ed
      Yaowu Xu authored 
      Change-Id: Ibc7933fba85feeb30ef9b14b302d932aff19f54e
      bf4202ed
  17. 28 Jan, 2016 1 commit
  19. 21 Jan, 2016 1 commit
  21. 13 Jan, 2016 1 commit
  23. 25 Nov, 2015 1 commit
    • Alex Converse's avatar
      Change highbd variance rounding to prevent negative variance. · 022c848b
      Alex Converse authored 
      Always round sum error and sum square error toward zero in variance
calculations. This prevents variance from becoming negative.
Avoiding rounding variance at all might be better but would be far
more invasive.

Change-Id: Icf24e0e75ff94952fc026ba6a4d26adf8d373f1c
      022c848b
  25. 06 Nov, 2015 1 commit
  27. 30 Jul, 2015 1 commit
  29. 08 Jul, 2015 1 commit
  31. 07 Jul, 2015 1 commit
  33. 06 Jul, 2015 1 commit
  35. 02 Jul, 2015 2 commits
  37. 01 Jul, 2015 2 commits
  39. 30 Jun, 2015 1 commit
  41. 12 Jun, 2015 1 commit
  43. 06 Jun, 2015 1 commit
    • James Zern's avatar
      disable vp8_sub_pixel_variance8x8_neon · 47fe5354
      James Zern authored 
      fails unit tests:
[  FAILED  ] NEON/VP8SubpelVarianceTest.ExtremeRef/0, where GetParam() = (3, 3, 0x14e36d, 0)
[  FAILED  ] NEON/VP8SubpelVarianceTest.Ref/0, where GetParam() = (3, 3, 0x14e36d, 0)

the tests were recently enabled in:
eb88b172 Make vp9 subpixel match vp8

the functions likely haven't changed since being converted from assembly

Change-Id: I6141717b111b8f735f436c160d74270af53ef722
      47fe5354
  45. 04 Jun, 2015 1 commit
    • Johann's avatar
      Make vp9 subpixel match vp8 · eb88b172
      Johann authored 
      The only difference between the two was that the vp9 function allowed
for every step in the bilinear filter (16 steps) while vp8 only allowed
for half of those. Since all the call sites in vp9 (<< 1) the input, it
only ever used the same steps as vp8.

This will allow moving the subpel variance to vpx_dsp with the rest of
the variance functions.

Change-Id: I6fa2509350a2dc610c46b3e15bde98a15a084b75
      eb88b172
  47. 02 Jun, 2015 1 commit
  49. 01 Jun, 2015 1 commit
    • Johann's avatar
      Cast variance reference output · fdc54999
      Johann authored 
      The larger internal variables are required for the intermediates
but RoundHighBitDepth brings them down to uint32_t/unsigned int.

Fixes type warnings in visual studio.

Change-Id: I48d35284d6cbde330ccdc1f46b6215a645d5eb00
      fdc54999
  51. 28 May, 2015 2 commits
  53. 27 May, 2015 1 commit
  55. 26 May, 2015 1 commit
  57. 13 May, 2015 1 commit
    • Johann's avatar
      Relocate memory operations for common code · 1d7ccd53
      Johann authored 
      With the sad functions, and hopefully the variance functions soon,
moving to the vpx_dsp location, place the defines used in the
reference C code in a common location.

Change-Id: I4c8ce7778eb38a0a3ee674d2f1c488eda01cfeca
      1d7ccd53
  59. 14 Jan, 2015 1 commit
    • Frank Galligan's avatar
      Add 64x64 sub_pel_variance Neon function · ec1d8387
      Frank Galligan authored 
      On Nexus 7 speed -5, -6, -7, and -8 saw about a 15% increase
in perf for 480p. Speeds -5, -6, -7, and -8 saw about a 10%
increase in perf for 720p.

Tested on Nexus 7, built with ndk r10d, gcc 4.9.

Change-Id: I2fa5315845e3021c9a6e2ea47e52e68b398d8334
      ec1d8387
  61. 13 Jan, 2015 1 commit
    • Frank Galligan's avatar
      Add 64x variance Neon functions · 74d40cd5
      Frank Galligan authored 
      Add optimized Neon functions of:
vp9_variance32x64
vp9_variance64x32
vp9_variance64x64

On Nexus 7 speed -5 and -6 saw about a 4% increase in perf.
Speeds -7 and -8 saw about a 6% increase in perf.
Tested on Nexus 7, built with ndk r10d, gcc 4.9.

Change-Id: I5a81f13c9897eb927fa39662530f5524a0f768fa
      74d40cd5
  63. 14 Nov, 2014 1 commit
  65. 15 Sep, 2014 1 commit