Age | Commit message (Collapse) | Author |
|
Change-Id: I7605b6678014a5426ceb45c27b54885e0c4e06ed
|
|
Change-Id: Icc7a816491897107764e4c936288e9000e6319b8
|
|
The intrinsics version of the pair quant is slower than running it
individually.
Change-Id: I7b4ea8599d4aab04be0a5a0c59b8b29a7fc283f4
|
|
Change-Id: I59ef7c49f72d2d40bbe5b56af11bdf5f9ae2f1b8
|
|
Change-Id: I96ed73e109c4f89dd06f3583cf7ecf9277401fae
|
|
Change-Id: I252f5f8a5d5ada65da08699774a7bb1eb2bd5b2e
|
|
Change-Id: I82834550503a43ff7ec8422342dc65136453b287
|
|
Remove dependency of this function on asm_offsets. ssse3/sse4 next.
Change quant_shift calculation so it be done using SIMD. Pre-calculate
as much as possible to simplify EOB selection.
Take advantage of qcoeff being zero'd by tying the if statements
together.
Speed parity with previous implementation with gcc x86_64 linux
Change-Id: Ife97556a1eca3a74b09def1a3d04084974dff1fb
|
|
Change-Id: Ic9956ddf1c2ddffcf7be7fdfc23ad9a2426fc47a
WIP: Fixing unsafe threading in VP8 encoder.
|
|
Fixing unsafe threading in VP8 encoder.
Change-Id: Ibf4c89a2043654834747811bc11eb283de0bb830
|
|
Change-Id: I76fe20ade099573997404b8733cf7f79e82fb21e
WIP: Fixing unsafe threading in VP8 encoder.
|
|
Change-Id: Ifa78c0a953fab3e5dd7af0446924846c7022cd09
|
|
|
|
Change-Id: I44e4e3869f231ae270cca98c9565f23c512e3ddf
|
|
Change-Id: I650a593162280ab40e71e527ec6518303e2d5723
|
|
Change-Id: I28ac1519d1594801fef9a623cb64598d3d751eb0
|
|
Change-Id: Ie22841d096f3c86694b95bd06fc3a8ce1f032a10
|
|
Change-Id: Ib73c7b2bee4cb2eb2528fa6b381fffe9503079a0
|
|
Change-Id: Ie9a26be7c9baa54a0e43a63ed6c77f2746477a9c
|
|
Change-Id: I289564a5a27f0d03ddc6f19c7838542ff22719be
|
|
Allows building the library with the gcc -pedantic option, for improved
portabilty. In particular, this commit removes usage of C99/C++ style
single-line comments and dynamic struct initializers. This is a
continuation of the work done in commit 97b766a46, which removed most
of these warnings for decode only builds.
Change-Id: Id453d9c1d9f44cc0381b10c3869fabb0184d5966
|
|
This extends the denoiser to work for temporally scalable
coding.
I believe this also fixes a very rare but really bad bug in the original
implementation.
Change-Id: I8b3593a8c54b86eb76f785af1970935f7d56262a
|
|
Change-Id: If6e11ba3d681e831d7d98662c0abdd2ac16b3811
|
|
RD costs were local to MACROBLOCK data and had to be copied all the
time to each thread's MACROBLOCK data. Tables moved to a common place
and only pointers are setup for each encoding thread.
vp8_cost_tokens() generates 'int' costs so changed all types to be
int (i.e. removed unsigned).
NOTE: Could do some more cleaning in vp8cx_init_mbrthread_data().
Change-Id: Ifa4de4c6286dffaca7ed3082041fe5af1345ddc0
|
|
Change-Id: I05788522e9cde4322cfb12032483bdbf184bdf0b
|
|
This commit continues the process of converting to the new RTCD
system.
Change-Id: Iba9df4c03a508e51c37201c621be43523fae87d9
|
|
This commit continues the process of converting to the new RTCD
system.
Change-Id: I3f9c07db65eb206f6363d21bdb80e871570da767
|
|
Change-Id: Ie2dc0d72363ff38e0f71b59f6e2d1a2d70c5266b
|
|
Change-Id: I72ed49ce14ca0124dd0d31bfcf4c7630a4681587
|
|
In some situations (f.g. error-resilient is turned on), vp8cx_mb
_init_quantizer() was called once per macroblock. Added checks
to avoid calculations when there is no change.
Change-Id: Ie4f0a5ade2202041254990a4e9d5b03bd1ac5aea
|
|
|
|
There were many instances in the code of vp8_coef_tokens and
vp8_coef_tokens-1, which was a preprocessor macro despite the naming
convention. Replace these with MAX_ENTROPY_TOKENS and ENTROPY_NODES,
respectively.
Change-Id: I72c4f6c7634c94e1fa066cd511471e5592c748da
|
|
I got this idea from Pascal (Thanks). Before encoding a macroblock,
copy it to a 16x16 buffer, and then read source data from there
instead. This will help keep the source data in cache, and help
with the performance.
Change-Id: Id05f4cb601299150511d59dcba0ae62c49b5b757
|
|
|
|
Declared the bmi in BLOCKD as a union instead of B_MODE_INFO.
Then removed B_MODE_INFO completely.
Change-Id: Ieb7469899e265892c66f7aeac87b7f2bf38e7a67
|
|
vp8_fast_quantize_b_pair_neon function added to quantize
two adjacent blocks at the same time to improve performance.
- Additional 3-6% speedup compared to neon optimized fast
quantizer (Tanya VGA@30fps, 1Mbps stream, cpu-used=-5..-16)
Change-Id: I3fcbf141e5d05e9118c38ca37310458afbabaa4e
|
|
Various members that were either completely unreferenced or written
and not read.
Change-Id: Ie41ebac0ff0364a76f287586e4fe09a68907806e
|
|
This commit restructures the mb activity masking code
to better facilitate experimentation using different metrics
etc. and also allows for adjustment of the zero bin either
for encode only or both the encode and mode selection
stages
It also uses information from the current frame rather than
the previous frame and the default strength has been
reduced.
Change-Id: Id39b19eace37574dc429f25aae810c203709629b
|
|
in encodframe.c, quant_shift is set to 0 or 1 in vp8cx_invert_quant
only use 8 bits to store this, instead of 16. will allow saving an
xmm register in an updated version of the regular quantize
Change-Id: Ie88c47fe2aff5af0283dab1147fb2791e4b12f90
|
|
MV sad cost error is only used in full-pixel motion search,
which only need full-pixel resolution instead of quarter-pixel
resolution. This change reduced mvsadcost table size, and
removed unneccessary pamameter passing since this table is
constant once it is generated.
Change-Id: I9f931e55f6abc3c99011321f1dfb2f3562e6f6b0
|
|
Allow compiling without adding vp8/{common,encoder,decoder} to the
include paths.
Change-Id: Ifeb5dac351cdfadcd659736f5158b315a0030b6c
|
|
vp8cx_mb_init_quantizer was being called for every mode checked
in vp8_rd_pick_inter_mode. zbin_extra is the only value that
really needs to be recalculated. This calculation is disabled
when using the fast quantizer for mode selection.
This gave a small performance boost (~.5% to 1%).
Note: This needs to be verified with segmentation_enabled.
Change-Id: I62716a870b3c82b4a998bdf95130ff0b02106f1e
|
|
Use the fast quantizer for inter mode selection and the
regular quantizer for the rest of the encode for good quality,
speed 1. Both performance and quality were improved. The
quality gains will make up for the quality loss mentioned in
I9dc089007ca08129fb6c11fe7692777ebb8647b0.
Change-Id: Ia90bc9cf326a7c65d60d31fa32f6465ab6984d21
|
|
Merge commit 'refs/changes/79/779/2' of
https://review.webmproject.org/p/libvpx
Conflicts:
vp8/encoder/encodeintra.c
vp8/encoder/encodemb.c
Change-Id: Id607063fabe92d99eeb3c380e8ca670b01bfb3ef
|
|
Most of the code that actually uses these matrices indexes them as
if they were a single contiguous array, and coverity produces
reports about the resulting accesses that overflow the static
bounds of the first row.
This is perfectly legal in C, but converting them to actual [16]
arrays should eliminate the report, and removes a good deal of
extraneous indexing and address operators from the code.
Change-Id: Ibda479e2232b3e51f9edf3b355b8640520fdbf23
|
|
This uses MB variance to change the RDO weight for mode decision
and quantization.
Activity is normalized against the average for the frame, which is
currently tracked using feed-forward statistics.
This could also be used to adjust the quantizer for the entire
frame, but that requires more extensive rate control changes.
This does not yet attempt to adapt the quantizer within the frame,
but the signaling cost means that will likely only be useful at
very high rates.
Change-Id: I26cd7c755cac3ff33cfe0688b1da50b2b87b9c93
|
|
Changes 'The VP8 project' to 'The WebM project', for consistency
with other webmproject.org repositories.
Fixes issue #97.
Change-Id: I37c13ed5fbdb9d334ceef71c6350e9febed9bbba
|
|
Moved partition_bmi and partition_count out of MB_MODE_INFO and
placed into MACROBLOCK. Also reduced the size of other members
of the MB_MODE_INFO struct. For 1080p, the memory was reduced
by 1,209,516 bytes. The decoder performance appeared to improve
by 3% for the clip used.
Note: The main goal for this change is to improve the decoder
performance. The encoder will be revisited at a later date for
further structure cleanup.
Change-Id: I4733621292ee9cc3fffa4046cb3fd4d99bd14613
|
|
The gf_active code is only used by the encoder, so it was moved from
common and decoder.
Change-Id: Iada15acd5b2b33ff70c34668ca87d4cfd0d05025
|
|
This replaces the approximate division-by-multiplication in the
quantizer with an exact one that costs just one add and one
shift extra.
The asm versions have not been updated in this patch, and thus
have been disabled, since the new method requires different
multipliers which are not compatible with the old method.
Change-Id: I53ac887af0f969d906e464c88b1f4be69c6b1206
|