Removed three members from the VP9_COMP data structure:
inter_zz_count, gf_bad_count, gf_update_recommended.

These were part of the VP8 real-time mode implementation
that was removed from the initial VP9 codecbase.

Change-Id: I866b083b88ef02c74837277d50ce532ca88492f3

Update best_inter_rd and best_inter_ref_frame only in single ref
frame case.

Change-Id: Id56825b231a62d6852bd83811410c05a7569f715

removes a textrel for sh_b23456789abcdefff

Change-Id: I80cb9dfd8e49a0fe884c8ff76472275b3a00cb57

Also removed unused declaration related 6 tap filter

Change-Id: Ic17f516141d885157918505f4204081e4c951fad

1. Reduced the size memset based on eob for 32x32 transform. The reset
of non-zero coefficient should probably go into where they are read in
inverse transform functions. (TODO)
2. Removed a redundant level of indirection.
vp9_iht4x4_add() checks transform type and call vp9_iht4x4_16_add()
for tranforms other than DCT_DCT. In this case, the DCT_DCT case
has been already handled here.

Change-Id: Iacbc77da761f0b308df5acea0f20c9add9f33d20

Change-Id: I529c634db4f81ba5386092c126f53312b1e51b2b

Making code easier to read and avoiding calculation of skip context twice.

Change-Id: I42c376b1a1811bc842bf6420bf81d2de7a1bf980

Change-Id: I12c67c8c0fa1aa7fb3f7d6cc2ef65be29c4ea292

The change doesn't affect the bitstream. It changes the order or function
calls and affects how we reconstruct intra- and inter-blocks. Speed up is
about 1...1.5%.

For intra-blocks:
  Before:
    for each transform block read tokens
    for each transform block do prediction
    for each transform block do inverse transform
  Now:
    for each transform block
      read tokens
      do prediction
      do inverse transform

For inter-blocks:
  Before:
    for each transform block read tokens
    for each transform block do inverse transform
  Now:
    for each transform block
      read tokens
      do inverse transform

Change-Id: I12a79bf1aa5a18c351b8010369bd3ff1deae1570

This CL contains two AVX2 optimized loop filter functions,
mb_lpf_horizontal_edge_w_avx2_8 and mb_lpf_horizontal_edge_w_avx2_16.

Change-Id: I604e4fe6e99752b7800c2ea98721d97f7e0b931b

   -Don't reduce maxQ for gold/alt in CBR mode.

   -Fix to min/maxQ for first/initial key frame.

   -Add more speeds to datarate test and reduce the starting bitrate for test.

Change-Id: Id2a333d76dd3f6a51b322ca984588e2a22159c58

Change-Id: I9781a62bc1a4cd9176554d1271d87dbcafda9cb0

This commit makes zcoeff_blk cache the case where the entire block
is quantized to be zero (without applying zero-forcing) in the rate-
distortion optimization loop, and skip the forward DCT, quantization,
inverse DCT, and reconstruction process in the encode_block stage.

It now works for all the block sizes, including sub8x8 blocks.

Change-Id: I5ae60a9c436ba3637d11666733554bec4580ef98

Both decode_modes_sb and decode_modes_b had conditions to immediately
return at the beginning. Eliminating these conditions here and calling
these functions only to do a real work. Also unrolling loop for
PARTITION_SPLIT.

Change-Id: I2fc41cb74ac491f045a2f04fe68d30ff4aaa555d

fixes a crash in assembly on 32-bit linux/windows

Change-Id: I0c27e6c0ece9732b5eb2ee5b59ff42c3c8016c50

"<< SUBPEL_BITS" needs to be added in the calculation. Call
set_scaled_offsets() to calculate x_offset_q4 and y_offset_q4.

Change-Id: Ied130ea771510e918f51cd1dc3abe57f4c0962b5

tiles are decoded in parallel within a single frame

Change-Id: I7aca87cb1c239b74eceef72bdc9f672faebac373

factorizes the code in decode_tiles(). reading the offsets backwards
wasn't doing anything to prove tile independence

Change-Id: I0395d3c77205852ebdc55efedc68291e93cef85c

Change-Id: I56f8c50ac382202f66040cd9cfaa05d889572fc7