Commit Graph

174 Commits

Author SHA1 Message Date
Dmitry Kovalev
1e766b50e2 Giving consistent names to IDCT 32x32 functions.
Renames:
  vp9_short_idct32x32_add   -> vp9_idct32x32_1024_add
  vp9_short_idct32x32_1_add -> vp9_idct32x32_1_add
  vp9_idct_add_32x32        -> vp9_idct32x32_add

Change-Id: Id85306f5814bac6c47463a6b5901a93082510666
2013-10-10 11:27:39 -07:00
Dmitry Kovalev
1e8fc24af8 Merge "Removing inv_txm4x4_1_add and inv_txm4x4_add function pointers." 2013-10-10 10:49:27 -07:00
Dmitry Kovalev
419c3f6fba Merge "Giving consistent names to IDCT 16x16 functions." 2013-10-10 10:43:14 -07:00
Dmitry Kovalev
c983c966cb Removing inv_txm4x4_1_add and inv_txm4x4_add function pointers.
We already have itxm_add member in MACROBLOCKD structure. Both
inv_txm4x4_1_add and inv_txm4x4_add are just its special cases for
different eob values. But eob logic is already implemented in
vp9_iwht4x4_add and vp9_idct4x4_add (that's why also removing
inverse_transform_b_4x4_add).

Change-Id: I80bec9b6f7d40c5e5033c613faca5c819c3e6326
2013-10-08 11:27:56 -07:00
Dmitry Kovalev
8d3ef287a2 Merge "Removing redundant vp9_pt_energy_class declarations." 2013-10-08 10:54:48 -07:00
Dmitry Kovalev
b096c5a336 Giving consistent names to IDCT 16x16 functions.
Renames:
  vp9_short_idct16x16_add    -> vp9_idct16x16_256_add
  vp9_short_idct16x16_10_add -> vp9_idct16x16_10_add
  vp9_short_idct16x16_1_add  -> vp9_idct16x16_1_add
  vp9_idct_add_16x16         -> vp9_idct16x16_add

Change-Id: Ief8a3904de78deab0f4ede944c4d0339c228cfc3
2013-10-07 14:31:10 -07:00
Dmitry Kovalev
23cc1cd8e6 Removing redundant vp9_pt_energy_class declarations.
Declaring vp9_pt_energy_class in vp9_entropy.h instead of many external
places.

Change-Id: I66e8a3fc119a43f88d130d0dae4133c825a047a3
2013-10-07 14:11:01 -07:00
Dmitry Kovalev
c6ad70d5f1 Giving consistent names to IDCT 8x8 functions.
Renames:
  vp9_short_idct8x8_add    -> vp9_idct8x8_64_add
  vp9_short_idct8x8_1_add  -> vp9_idct8x8_1_add
  vp9_short_idct8x8_10_add -> vp9_idct8x8_10_add
  vp9_idct_add_8x8         -> vp9_idct8x8_add

Change-Id: Ifb8d3a45b4c0397aa805b30463f3d14581bf72c1
2013-10-06 00:24:09 -07:00
Jim Bankoski
bf21ce63ee encodemb cpplint issues revisited.
Change-Id: Id5f25b74e2207bf44b6f6c8ffe548fa30fd78b4d
2013-10-05 17:24:51 -07:00
Dmitry Kovalev
be7eec79be Moving all idct/iht functions in one place.
Moving functions from vp9_idct_blk to vp9_idct because these functions are
used from both encoder and decoder. Removing duplicated code from
vp9_encodemb.c and reusing existing functions.

Change-Id: Ia0a6782f8c4c409efb891651b871dd4bf22d5fe8
2013-10-02 14:13:33 -07:00
Dmitry Kovalev
b3d3578ee4 Merge "Renaming vp9_short_idct10_8x8_add to vp9_short_idct8x8_10_add." 2013-09-29 12:01:50 -07:00
Dmitry Kovalev
3fab2125ff Renaming vp9_short_idct10_8x8_add to vp9_short_idct8x8_10_add.
Making name consistent with vp9_short_idct8x8 and vp9_short_idct8x8_1.

Change-Id: I99e0be040ec893f9571dcf090e18f98dc58339f5
2013-09-27 15:26:27 -07:00
Dmitry Kovalev
209c6cbf8f Removing vp9_get_coef_neighbors_handle function.
Change-Id: I6be72c8b048d1ccc7ef43764cf84c32360098970
2013-09-27 14:11:13 -07:00
Dmitry Kovalev
15a36a0a0d Renaming vp9_short_idct10_16x16 to vp9_short_idct16x16_10.
Making function name consistent with vp9_short_idct16x16 and
vp9_short_idct16x16_1.

Change-Id: I70e54be9e6b9a1dddab0de470686591e96d05517
2013-09-26 14:01:25 -07:00
Dmitry Kovalev
d445945a84 Adding vp9_get_entropy_contexts function.
Change-Id: Ife0dd29fb4ad65c7e12ac5f1db8cea4ed81de488
2013-09-24 17:26:05 -07:00
Jingning Han
a517343ca3 Enable per transformed block zero coeffs forcing
This commit enables forcing all coefficients zero per transformed
block, when its rate-distortion cost is lower than regular coeff
quantization.

The overall performance improvement (including its parent patch on
calculating rd cost per transformed block) at speed 1:
derf:  0.298%
yt:    0.452%
hd:    0.741%
stdhd: 0.006%

Change-Id: I66005fe0fd7af192c3eba32e02fd6d77952accb5
2013-09-23 10:39:35 -07:00
Dmitry Kovalev
a23c2a9e7b Adding get_scan_and_band function.
Extracting get_scan_and_band function from get_entropy_context to
remove duplicated code.

Change-Id: I5da1f5a60263017e887da68bc834317b5f084cb2
2013-09-19 16:53:48 +04:00
Scott LaVarnway
ac6093d179 New mode_info_context storage -- undo revert
mode_info_context was stored as a grid of MODE_INFO structs.
The grid now constists of pointers to MODE_INFO structs.  The
MODE_INFO structs are now stored as a stream (decoder only),
eliminating unnecessary copies and is a little more cache
friendly.

Change-Id: I031d376284c6eb98a38ad5595b797f048a6cfc0d
2013-09-11 13:45:44 -04:00
James Zern
c1913c9cf4 Merge "Revert "New mode_info_context storage"" 2013-09-09 14:38:01 -07:00
James Zern
54a03e20dd Revert "New mode_info_context storage"
This reverts commit dae17734ec

Encode crashes, leaks and increases integer overflow errors.

Change-Id: I595aa2649bb8d0b6552ff91652837a74c103fda2
2013-09-09 13:37:01 -07:00
Jim Bankoski
e378566060 Merge "New mode_info_context storage" 2013-09-08 07:16:25 -07:00
Jingning Han
09bc942b47 Fix overflow issue in 16x16 quantization SSSE3
The 16x16 transform unit test suggested that the peak coefficient
value can reach 32639. This could cause potential overflow issue
in the SSSE3 implmentation of 16x16 block quantization. This commit
fixes this issue by replacing addition with saturated addition.

Change-Id: I6d5bb7c5faad4a927be53292324bd2728690717e
2013-09-06 21:06:10 -07:00
Scott LaVarnway
dae17734ec New mode_info_context storage
mode_info_context was stored as a grid of MODE_INFO structs.
The grid now constists of a pointer to a MODE_INFO struct and
a "in the image" flag.  The MODE_INFO structs are now stored
as a stream, eliminating unnecessary copies and is a little
more cache friendly.

For the test clips used, the decoder performance improved
by ~4.3% (1080p) and ~9.7% (720p).

Patch Set 2: Re-encoded clips with latest. Now ~1.7% (1080p)
and 5.9% (720p).

Change-Id: I846f29e88610fce2523ca697a9a9ef2a182e9256
2013-09-06 12:33:34 -04:00
Dmitry Kovalev
851a2fd72c Renaming txfm_size to tx_size.
Change-Id: I752e374867d459960995b24d197301d65ad535e3
2013-08-27 19:47:53 -07:00
Dmitry Kovalev
7b95f9bf39 Renaming BLOCK_SIZE_TYPE to BLOCK_SIZE in the encoder.
Change-Id: I62bb07c377f947cb72fac68add7a6b199e42c6b9
2013-08-27 11:05:08 -07:00
Dmitry Kovalev
be60924f29 Cleaning up optimize_init_b function.
Change-Id: Ib2c975e1d96deefb7ac4d6b600c8c5388035d111
2013-08-21 16:40:16 -07:00
Dmitry Kovalev
82d4d9a008 Passing plane_bsize to foreach_transformed_block_visitor.
Updating all foreach_transformed_block_visitor functions to work with
plane block size instead of general block. Removing a lot of duplicated
code.

Change-Id: I6a9069e27528c611f5a648e1da0c5a5fd17f1bb4
2013-08-19 15:47:24 -07:00
Dmitry Kovalev
2e3478a593 Using plane_bsize instead of bsize.
This change set is intermediate. The next one will remove all repetitive
plane_bsize calculations, because it will be passed as argument to
foreach_transformed_block_visitor.

Change-Id: Ifc12e0b330e017c6851a28746b3a5460b9bf7f0b
2013-08-19 13:20:21 -07:00
Dmitry Kovalev
26e5b5e25d Removing unused or redundant arguments from *_args structures.
Redundant dst, pre[2] from build_inter_predictors_args, unused cm from
encode_b_args.

Change-Id: I2c476cd328c5c0cca4c78ba451ca6ba2a2c37e2d
2013-08-16 12:51:20 -07:00
Dmitry Kovalev
afd9bd3e3c Moving from ss_txfrm_size to tx_size.
Updating foreach_transformed_block_visitor and corresponding functions
to accept tx_size instead of ss_txfrm_size. List of functions per file:

vp9_decodframe.c
  decode_block
  decode_block_intra

vp9_detokenize.c
  decode_block

vp9_encodemb.c
  optimize_block
  vp9_xform_quant
  vp9_encode_block_intra

vp9_rdopt.c
  dist_block
  rate_block
  block_yrd_txfm

vp9_tokenize.c
  set_entropy_context_b
  tokenize_b
  is_skippable

Change-Id: I351bf563eb36cf34db71c3f06b9bbc9a61b55b73
2013-08-15 17:03:03 -07:00
Dmitry Kovalev
bb3b817c1e Converting code from using ss_txfrm_size to tx_size.
Updated function signatures:
  txfrm_block_to_raster_block
  txfrm_block_to_raster_xy
  extend_for_intra
  vp9_optimize_b

Change-Id: I7213f4c4b1b9ec802f90621d5ba61d5e4dac5e0a
2013-08-15 11:44:57 -07:00
Dmitry Kovalev
bb072000e8 foreach_transformed_block_in_plane cleanup, explicit tx_size var.
Making foreach_transformed_block_in_plane more clear (it's not finished
yet). Using explicit tx_size variable consistently instead of
(ss_txfrm_size / 2) or (ss_txfrm_size >> 1) expression.

Change-Id: I1b9bba2c0a9f817fca72c88324bbe6004766fb7d
2013-08-14 11:39:31 -07:00
Dmitry Kovalev
f1559bdeaf Inlining 16 as a stride for BLOCK_OFFSET macro.
Change-Id: I7f23d174eb089e5500f268a10db09648634c1b82
2013-08-09 16:40:05 -07:00
Dmitry Kovalev
cd0629fe68 Merge "Removing plane_block_{width, height}_log2by4 functions." 2013-08-09 15:26:51 -07:00
Dmitry Kovalev
61c33d0ad5 Removing plane_block_{width, height}_log2by4 functions.
Change-Id: I040b82b8e32aee272d10cbb021c7ba1c76343d7a
2013-08-07 17:06:33 -07:00
Jingning Han
debb9c68c8 Use low precision 32x32fdct for encodemb in speed1
The low precision 32x32 fdct has all the intermediate steps within
16-bit depth, hence allowing faster SSE2 implementation, at the
expense of larger round-trip error. It was used in the rate-distortion
optimization search loop only.

Using the low precision version, in replace of the high precision one,
affects the compression performance by about 0.7% (derf, stdhd) at
speed 0. For speed 1, it makes derf set down by only 0.017%.

Change-Id: I4e7d18fac5bea5317b91c8e7dabae143bc6b5c8b
2013-08-07 15:34:12 -07:00
Dmitry Kovalev
d007446b3f Replacing long block size enum values with shorter ones (2).
Change-Id: I428c4d42212b757112e3acfe5b81314cfbb5fd6b
2013-08-05 10:51:02 -07:00
Dmitry Kovalev
680ec32d18 Adding is_inter_block function.
Using it instead of long unclear verbose check
"mbmi->ref_frame[0] != INTRA_FRAME".

Change-Id: I9c7b4b3797942fa962bf3ba7460fff3084beabe9
2013-08-02 16:25:33 -07:00
Dmitry Kovalev
ce8dedc353 Cleanup: removing unused function arguments.
Change-Id: I27471768980fc631916069f24bc7c482a5c9ca17
2013-08-01 13:41:38 -07:00
Jingning Han
a7c4de22e1 16x16 inverse 2D-DCT with DC only
This commit provides special handle on 16x16 inverse 2D-DCT, where
only DC coefficient is quantized to be non-zero value.

Change-Id: I7bf71be7fa13384fab453dc8742b5b50e77a277c
2013-07-29 14:45:53 -07:00
Jingning Han
decb1b94de Merge "Shortcut 8x8/16x16 inverse 2D-DCT" 2013-07-29 11:04:07 -07:00
Ronald S. Bultje
118ccdcd30 Inverse dimension order in token_cost array.
This allows us to increment the position at the band-level only as
we go from one band to the next; more importantly, that allows us to
use an add instead of multiply instruction, and omit the instruction
altogether if the band doesn't change from one coef to the next, thus
being slightly faster (probably more noticeable on systems where a
multiply is expensive, like arm).

Change-Id: I4343fe35b9f9a47fa00b217bdcbf5f91ff96c381
2013-07-26 17:30:04 -07:00
Jingning Han
38fa487164 Shortcut 8x8/16x16 inverse 2D-DCT
This commit brought back the shortcut implementation of 8x8/16x16
inverse 2D-DCT. When the eob <= 10, it skips the inverse transform
operations on row 4:7/4:15 in the first round. For bus_cif at 1000
kbps, this provides about 2% speed-up at speed 0.

Change-Id: I453e2d72956467d75be4ad8c04b4482ab889d572
2013-07-26 17:19:14 -07:00
Jingning Han
325e0aa650 Special handle on DC only inverse 8x8 2D-DCT
This commit enables a special handle for the 8x8 inverse 2D-DCT,
where only DC coefficient is quantized to be non-zero. For bus_cif
at 2000 kbps, it provides about 1% speed-up at speed 0.

Change-Id: I2523222359eec26b144cf8fd4c63a4ad63b1b011
2013-07-26 14:16:51 -07:00
Jingning Han
2f58faffa4 Make coeff_optimize initialized per-plane
This commit makes the initialization of trellis coeff optimization
a per-plane operation, thereby eliminating the redundant steps in
encode_sby and encode_sbuv. It makes the encoder at speed 0 slightly
faster.

Change-Id: Iffe9faca6a109dafc0dd69dc7273cbdec19b17cd
2013-07-25 11:44:29 -07:00
Dmitry Kovalev
9139ee0908 Adding condition inside get_tx_type_{4x4, 8x8, 16x16}.
Adding plane type check condition because it was always used outside of
get_tx_type_{4x4, 8x8, 16x16}.

Change-Id: I02f0bbfee8063474865bd903eb25b54d26e07230
2013-07-24 12:55:45 -07:00
Jingning Han
666c266623 Merge "Unify the use of encode_b_args/optimize_block_args" 2013-07-23 18:08:50 -07:00
Jingning Han
ab77828b36 Unify the use of encode_b_args/optimize_block_args
The struct optimize_block_args is defined same as encode_b_args.
Remove this redundant definition, and use encode_b_args consistently.

Change-Id: I1703aeeb3bacf92e98a34f4355202712110173d9
2013-07-23 16:04:02 -07:00
Jingning Han
e9e2fe8ec3 Make xform_quant operations tx_type independent
The xform_quant() module is only used by inter modes, hence removing
the redundant switches therein conditioned on tx_type.

Change-Id: Ib87ce5b2f2e4cbf3ceb133a1108afa173c933a3f
2013-07-23 12:37:25 -07:00
Jingning Han
0359ad7f9a Skip inverse transform when eob is zero
When all the transform coefficients were quantized to zero, skip
the inverse transform operation. For bus_cif at 1000 kbps, the
runtime goes from 154967ms -> 149842ms, i.e., about 3% speed-up,
at speed 0.

Change-Id: Ic0a813fff5e28972d4888ee42d8747846a6c3cc6
2013-07-23 10:06:41 -07:00