Refactor decode_tiles and loopfilter code.

The current decode_tiles decodes the frame one tile by one tile
and then loopfilter the whole frame or use another worker thread to
do loopfiltering.

|------|------|------|------|
|Tile1-|Tile2-|Tile3-|Tile4-|
|------|------|------|------|

For example, if a tile video has one row and four cols, decode_tiles
will decode the Tile1, then Tile2, then Tile3, then Tile4.
And during decode each tile, decode_tile will decode row by row in
each tile.

For frame parallel decoding, decode_tiles will decode video in row order
across the tiles. So the order will be:
"Decode 1st row of Tile1" -> "Decode 1st row of Tile2"
-> "Decode 1st row of Tile3" -> "Decode 1st row of Tile4"
-> "Decode 2nd row of Tile1" -> "Decode 2nd row of Tile2"
-> "Decode 2nd row of Tile3" -> "Decode 2nd row of Tile4"-> "loopfilter 1st row"

Change-Id: I2211f9adc6d142fbf411d491031203cb8a6dbf6b

1 files changed, 10 insertions, 1 deletions

diff --git a/vp9/decoder/vp9_decoder.h b/vp9/decoder/vp9_decoder.h
index d6cb5071d..36fb7ea94 100644
--- a/vp9/decoder/vp9_decoder.h
+++ b/vp9/decoder/vp9_decoder.h
@@ -27,6 +27,13 @@
 extern "C" {
 #endif
 
+// TODO(hkuang): combine this with TileWorkerData.
+typedef struct TileData {
+  VP9_COMMON *cm;
+  vp9_reader bit_reader;
+  DECLARE_ALIGNED(16, MACROBLOCKD, xd);
+} TileData;
+
 typedef struct VP9Decoder {
   DECLARE_ALIGNED(16, MACROBLOCKD, mb);
 
@@ -40,10 +47,12 @@ typedef struct VP9Decoder {
   int decoded_key_frame;
 
   VP9Worker lf_worker;
-
   VP9Worker *tile_workers;
   int num_tile_workers;
 
+  TileData *tile_data;
+  int total_tiles;
+
   VP9LfSync lf_row_sync;
 
   vpx_decrypt_cb decrypt_cb;