James Berry [Fri, 27 May 2011 18:57:25 +0000 (14:57 -0400)]
bug fix check frame buffer index before copy
in onyx_if.c update_reference_frames() make
sure that frame buffer indexes are not equal
before preforming a buffer copy. If two frames
share the same buffer the flags will already be
set correctly.
Change-Id: Ida9b5516d08e3435c90f131d2dc19d842cfb536e
Scott LaVarnway [Fri, 27 May 2011 14:52:04 +0000 (07:52 -0700)]
Merge "Broken EC after MODE_INFO size reduction"
Yunqing Wang [Fri, 27 May 2011 14:25:25 +0000 (07:25 -0700)]
Merge "Remove unused code"
Yunqing Wang [Fri, 27 May 2011 14:20:49 +0000 (10:20 -0400)]
Remove unused code
Hex search is not called in rdopt.c
Change-Id: I67347f03e13684147a7c77fb9e9147e440bb5e8e
Scott LaVarnway [Thu, 26 May 2011 19:13:00 +0000 (15:13 -0400)]
Broken EC after MODE_INFO size reduction
This patch fixes the compiler errors and the seg fault
when running decode_with_partial_drops.
Change-Id: I7c75369e2fef81d53b790d5dabc327218216838b
John Koleszar [Thu, 26 May 2011 16:58:26 +0000 (09:58 -0700)]
Merge "Do not copy data between encoder reference buffers."
Yaowu Xu [Thu, 26 May 2011 16:39:41 +0000 (09:39 -0700)]
Merge "fix the mix use of errorperbit and sadperbit"
Scott LaVarnway [Thu, 26 May 2011 14:01:38 +0000 (07:01 -0700)]
Merge "Use int_mv instead of MV in vp8_mv_cont"
Yaowu Xu [Wed, 25 May 2011 23:07:37 +0000 (16:07 -0700)]
fix the mix use of errorperbit and sadperbit
error_per_bit and sad_per_bit were designed as estimates of a bit worth
of sum squared error and sum absolute difference respectively. Under
this assumption, error_per_bit should be used in combination with 2nd
order errors (variance or sum squared error) while sad_per_bit should
be used in combination with 1st order SADs in motion estimation. There
were a few places where sad_per_bit has been misused with variances,
this commit changes to use error_per_bit for those places, also changes
parameter names to properly indicate which constant is being used.
On cif set, the change has a universal gain by all metrics: 0.13% by
average/overall psnr and 0.1% by ssim.
Change-Id: I4850fdcc3fd6886b30f784bd843f13dd401215fb
Yunqing Wang [Wed, 25 May 2011 18:35:42 +0000 (11:35 -0700)]
Merge " Use var8x8 instead of get8x8var in VP8_UVSSE"
Yunqing Wang [Wed, 25 May 2011 18:31:07 +0000 (11:31 -0700)]
Merge "Return sse value in vp8_variance SSE2 functions"
Yaowu Xu [Wed, 25 May 2011 16:35:54 +0000 (09:35 -0700)]
remove code not in use
Change-Id: I6e5e86235d341cce3b02abda26dbeb71940ed955
Yunqing Wang [Wed, 25 May 2011 13:26:29 +0000 (09:26 -0400)]
Return sse value in vp8_variance SSE2 functions
Minor modification.
Change-Id: I09511d38fd1451d5c4106a48acdb3f766ce59cb7
Attila Nagy [Wed, 25 May 2011 09:54:34 +0000 (12:54 +0300)]
Use var8x8 instead of get8x8var in VP8_UVSSE
'sum' returned by get8x8var is not used and var8x8 has optimizations
for more platforms.
Change-Id: I4a907fb1a05f285669fb0b95dc71d42182c980f6
Yunqing Wang [Tue, 24 May 2011 19:59:37 +0000 (15:59 -0400)]
Fix a bug happening while encoding at profile=3
While profile=3, there is no sub-pixel search. Distortion and SSE
have to calculated using get_inter_mbpred_error().
Change-Id: Ifb36e17eef7750af93efa7d0e2870142ef540184
Scott LaVarnway [Tue, 24 May 2011 20:01:12 +0000 (16:01 -0400)]
Use int_mv instead of MV in vp8_mv_cont
Less operations.
Change-Id: Ibb9cd5ae66b8c7c681c9a654d551c8729c31c3ae
Scott LaVarnway [Tue, 24 May 2011 19:17:03 +0000 (15:17 -0400)]
Removed unused variable warnings
Change-Id: I6e5e921f03dc15a72da89a457848d519647677a3
Scott LaVarnway [Tue, 24 May 2011 19:08:24 +0000 (12:08 -0700)]
Merge "MODE_INFO size reduction"
Scott LaVarnway [Tue, 24 May 2011 17:24:52 +0000 (13:24 -0400)]
MODE_INFO size reduction
Declared the bmi in MODE_INFO as a union instead of B_MODE_INFO.
This reduced the memory footprint by 518,400 bytes for 1080
resolutions. The decoder performance improved by ~4% for the
clip used and the encoder showed very small improvements. (0.5%)
This reduction was first mentioned to me by John K. and in a
later discussion by Yaowu.
This is WIP.
Change-Id: I8e175fdbc46d28c35277302a04bee4540efc8d29
John Koleszar [Tue, 24 May 2011 12:57:44 +0000 (05:57 -0700)]
Merge "Fixing bug in VP8_SET_REFERENCE decoder control command"
Yunqing Wang [Tue, 24 May 2011 12:26:16 +0000 (05:26 -0700)]
Merge "Rewrite hex search function"
Henrik Lundin [Mon, 23 May 2011 11:47:33 +0000 (13:47 +0200)]
Fixing bug in VP8_SET_REFERENCE decoder control command
In vp8dx_set_reference, the new reference image is written to an
unused reference frame buffer.
Change-Id: I9e4f2cef5a011094bb7ce7b2719cbfe096a773e8
Yaowu Xu [Mon, 23 May 2011 21:49:56 +0000 (14:49 -0700)]
Merge "use get8x8var directly for non-subpixel motion case in VP8_UVSSE"
Yunqing Wang [Fri, 20 May 2011 19:26:32 +0000 (15:26 -0400)]
Rewrite hex search function
Reduced some bound checks in hex search function.
Change-Id: Ie5f73a6c227590341c960a74dc508cff80f8aa06
Yaowu Xu [Sun, 22 May 2011 04:51:21 +0000 (21:51 -0700)]
use get8x8var directly for non-subpixel motion case in VP8_UVSSE
VP8_UVSSE mistakenly used subpixvar8x8 to calculate SSE for non-subpixl
motion cases.
Change-Id: I4a5398bb9ef39c211039f6af4540546d4972e6a9
John Koleszar [Fri, 20 May 2011 18:23:10 +0000 (11:23 -0700)]
Merge "bug fix active_worst_quality set below active_best_quality"
John Koleszar [Fri, 20 May 2011 18:20:44 +0000 (11:20 -0700)]
Merge "cleanup: collect twopass variables"
Johann [Fri, 20 May 2011 14:51:11 +0000 (07:51 -0700)]
Merge "Fixed iwalsh_neon build problems with RVDS4.1"
Yaowu Xu [Fri, 20 May 2011 14:45:42 +0000 (07:45 -0700)]
Merge "revise two function definitions with less parameters"
John Koleszar [Fri, 20 May 2011 14:39:03 +0000 (07:39 -0700)]
Merge "Remove unused members of VP8_COMP"
Yaowu Xu [Fri, 20 May 2011 01:37:13 +0000 (18:37 -0700)]
revise two function definitions with less parameters
Change-Id: Ia96e5bf915e4d3c0ac9c1795114bd9e5dd07327a
Yaowu Xu [Fri, 20 May 2011 00:25:31 +0000 (17:25 -0700)]
Merge "disable trellis optimization for first pass"
Yaowu Xu [Thu, 19 May 2011 23:00:28 +0000 (16:00 -0700)]
disable trellis optimization for first pass
also remove 2 #defines and 1 function declaration that are not in use.
Change-Id: I8f743d0e3dd9ebf1de24a8b0c30ff09f29b00c53
James Berry [Thu, 19 May 2011 22:02:48 +0000 (18:02 -0400)]
bug fix active_worst_quality set below active_best_quality
fixed a bug where active_worst_quality could be set
below active_best_quality which could result in an
infinite loop.
Change-Id: I93c229c3bc5bff2a82b4c33f41f8acf4dd194039
John Koleszar [Thu, 19 May 2011 21:16:39 +0000 (17:16 -0400)]
cleanup: collect twopass variables
This patch collects the twopass specific memebers of VP8_COMP into a
dedicated struct. This is a first step towards isolating the two pass
rate control and aids readability by decorating these variables with
the 'twopass.' namespace. This makes it clear to the reader in what
contexts the variable will be valid, and is a hint that a section of
code might be a good candidate to move to firstpass.c in later
refactoring. There likely will be other rate control modes that need
their own specific data as well.
This notation is probably overly verbose in firstpass.c, so an
alternative would be to access this struct through a pointer like
'rc->' instead of 'cpi->firstpass.' in that file. Feel free to make
a review comment to that effect if you prefer.
Change-Id: I0ab8254647cb4b493a77c16b5d236d0d4a94ca4d
Scott LaVarnway [Thu, 19 May 2011 20:22:59 +0000 (13:22 -0700)]
Merge "Using partition_info instead of blockd info for splitmv"
John Koleszar [Thu, 19 May 2011 18:42:24 +0000 (14:42 -0400)]
Remove unused members of VP8_COMP
Various members that were either completely unreferenced or written
and not read.
Change-Id: Ie41ebac0ff0364a76f287586e4fe09a68907806e
Scott LaVarnway [Thu, 19 May 2011 19:03:36 +0000 (15:03 -0400)]
Using partition_info instead of blockd info for splitmv
The partition_info struct contains info just for SPLITMV,
so it should be used instead of BLOCKD. Eventually, I want
to reduce the size of B_MODE_INFO struct found in BLOCKD, so
this is the first step toward that goal.
Also, since SPLITMV is not supported in vp8_pick_inter_mode(),
the unnecessary mem copies and checks were removed. For rt
encodes, this gave a slight performance improvement.
Change-Id: I5585c98fa9d5acbde1c7e0f452a01d9ecc080574
Scott LaVarnway [Thu, 19 May 2011 18:22:01 +0000 (11:22 -0700)]
Merge "Make hor UV predict ~2x faster (73 vs 132 cycles) using SSSE3."
John Koleszar [Thu, 19 May 2011 18:17:08 +0000 (11:17 -0700)]
Merge "changed configure option name to reduce confusion"
John Koleszar [Thu, 19 May 2011 18:12:18 +0000 (11:12 -0700)]
Merge "Make activity masking functions static"
John Koleszar [Thu, 19 May 2011 17:58:24 +0000 (10:58 -0700)]
Merge "Fix segv without --enable-error-concealment"
John Koleszar [Thu, 19 May 2011 17:57:45 +0000 (13:57 -0400)]
Fix segv without --enable-error-concealment
Missed wrapping one function call in #if CONFIG_ERROR_CONCEALMENT.
Change-Id: I5746b1e6e4531670dbed1130467331fe309bdcae
John Koleszar [Thu, 19 May 2011 17:48:58 +0000 (10:48 -0700)]
Merge "Adding error-concealment to the decoder."
Stefan Holmer [Mon, 2 May 2011 13:30:51 +0000 (15:30 +0200)]
Adding error-concealment to the decoder.
The error-concealer is plugged in after any motion vectors have been
decoded. It tries to estimate any missing motion vectors from the
motion vectors of the previous frame. Intra blocks with missing
residual are replaced with inter blocks with estimated motion vectors.
This feature was developed in a separate sandbox
(sandbox/holmer/error-concealment).
Change-Id: I5c8917b031078d79dbafd90f6006680e84a23412
John Koleszar [Thu, 19 May 2011 15:14:13 +0000 (11:14 -0400)]
Make activity masking functions static
These don't need extern linkage.
Change-Id: I21220ada926380a75ff654f24df84376ccc49323
John Koleszar [Thu, 19 May 2011 15:04:03 +0000 (11:04 -0400)]
Move quantizer init functions to quantize.c
Group related functions together.
Change-Id: I92fd779225b75a7204650f1decb713142c655d71
Attila Nagy [Tue, 17 May 2011 07:39:23 +0000 (10:39 +0300)]
Fixed iwalsh_neon build problems with RVDS4.1
rvct 4.1 was complaining about vstmia.16, store multiple expects 64 data type.
optimized the implementation.
Change-Id: I0701052cabd685c375637bbc3796ff6d88f5972c
Yunqing Wang [Wed, 18 May 2011 19:53:27 +0000 (12:53 -0700)]
Merge "Modify MVcount in pick_inter_mode to eliminate calling of vp8_find_near_mvs"
Yunqing Wang [Wed, 18 May 2011 13:52:56 +0000 (09:52 -0400)]
Fix a bug in vp8_clamp_mv function
Scott fixed the bug in MV clamping function in encoder, which
could cause artifacts.
Change-Id: Id05f2794c43c31cdd45e66179c8811f3ee452cb9
Yunqing Wang [Fri, 13 May 2011 14:56:45 +0000 (10:56 -0400)]
Modify MVcount in pick_inter_mode to eliminate calling of vp8_find_near_mvs
Moved MVcount modification in pick_inter_mode, and eliminated
calling of vp8_find_near_mvs.
Change-Id: Icd47448a1dfc8fdf526f86757d0e5a7f218cb5e8
John Koleszar [Fri, 13 May 2011 18:18:42 +0000 (11:18 -0700)]
Merge "Improve framerate adaptation"
Yaowu Xu [Fri, 13 May 2011 16:28:26 +0000 (09:28 -0700)]
Merge "adjusting rd constant slightly by ~10%"
Paul Wilkins [Fri, 13 May 2011 16:23:50 +0000 (09:23 -0700)]
Merge "Restructure of activity masking code."
Paul Wilkins [Thu, 12 May 2011 16:01:55 +0000 (17:01 +0100)]
Restructure of activity masking code.
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
John Koleszar [Thu, 12 May 2011 19:04:06 +0000 (15:04 -0400)]
Improve framerate adaptation
This patch improves the accuracy of frame rate estimation by using a
larger, 1 second window. It also more quickly adapts to step changes
in the input frame rate (ie 30fps to 15fps)
Change-Id: I39e48a8f5ac880b4c4b2ebd81049259b81a0218e
Scott LaVarnway [Thu, 12 May 2011 15:20:41 +0000 (11:20 -0400)]
Removed mv_bits_sadcost
This sad cost is being generated but never used.
Change-Id: I562eebdcb792b743770954feca365b5b37491ecd
Scott LaVarnway [Thu, 12 May 2011 14:50:16 +0000 (10:50 -0400)]
Using int_mv instead of MV
The compiler produces better assembly when using int_mv
for assignments. The compiler shifts and ors the two 16bit
values when assigning MV.
Change-Id: I52ce4bc2bfbfaf3f1151204b2f21e1e0654f960f
Yunqing Wang [Thu, 12 May 2011 14:20:44 +0000 (07:20 -0700)]
Merge "Modification and issue fix in full-pixel refining search"
Yunqing Wang [Wed, 11 May 2011 17:38:29 +0000 (13:38 -0400)]
Modification and issue fix in full-pixel refining search
Further modification and wrong implementation fix which caused
refining_search and refining_searchx4 result mismatching.
Change-Id: I80cb3a44bf5824413fd50c972e383eebb75f9b6f
Yaowu Xu [Thu, 12 May 2011 06:32:06 +0000 (23:32 -0700)]
adjusting rd constant slightly by ~10%
This is to reflect the RD improvement in the encoder. The change has a
small positive impact on quality (0.25% by VPXSSIM and 0.05% by PSNR)
Change-Id: Ic66ffc19b10870645088c0624c85556f009fd210
Yaowu Xu [Wed, 11 May 2011 03:20:59 +0000 (20:20 -0700)]
Merge "remove a variable no longer in use"
Yaowu Xu [Wed, 11 May 2011 02:59:52 +0000 (19:59 -0700)]
Merge "fix a bug related to gf_active_flags in multi-threaded encoder"
Yaowu Xu [Wed, 11 May 2011 02:57:51 +0000 (19:57 -0700)]
remove a variable no longer in use
The variable is introduced in commit
2e53e9e53 to make more use of
trellis quantization, but this is no longer necessary after RDMULT
was made adaptive in a number of later commits.
Change-Id: I7420522ec7723f38cf77033466c25afb405d52ae
John Koleszar [Wed, 11 May 2011 01:53:04 +0000 (18:53 -0700)]
Merge "Use stdint.h for VS2010"
Johann [Tue, 10 May 2011 19:58:56 +0000 (15:58 -0400)]
set up Global Offset Table in recon
global values were being referenced, but the GOT was not being set up.
as the GOT is only required for PIC, this issue wasn't caught in the
default configuration.
Change-Id: I8006e53776139362a76f2c80cf9d0f8458602b2f
http://code.google.com/p/webm/issues/detail?id=328
Yunqing Wang [Tue, 10 May 2011 13:59:38 +0000 (06:59 -0700)]
Merge "Use diamond search to replace full search in full-pixel refining search"
Yunqing Wang [Fri, 6 May 2011 16:51:31 +0000 (12:51 -0400)]
Use diamond search to replace full search in full-pixel refining search
In NEWMV mode, currently, full search is used as the refining search
after n-step search. By replacing it with an iterative diamond search
of radius 1 largely reduced the computation complexity, but still
maintained the same encoding quality since the refining search is
done for every macroblock instead of only a small precentage of
macroblocks while using full search.
Tests on the test set showed a 3.4% encoding speed increase with none
psnr & ssim loss.
Change-Id: Ife907d7eb9544d15c34f17dc6e4cfd97cb743d41
Johann [Mon, 9 May 2011 15:16:31 +0000 (11:16 -0400)]
clean up unused variable warnings
Change-Id: I9467d7a50eac32d8e8f3a2f26db818e47c93c94b
Yaowu Xu [Fri, 6 May 2011 16:00:44 +0000 (09:00 -0700)]
fix a bug related to gf_active_flags in multi-threaded encoder
Paul pointed out that the pointer to the gf_active_flags is not being
properly incremented in multithreaded encoder. This commit fixes the
issue by making sure the gf_active_ptr points to the starting of next
group of mb rows.
Change-Id: I3246e657d23beabb614dfb880733a68a5fd7e34c
John Koleszar [Fri, 6 May 2011 15:59:05 +0000 (08:59 -0700)]
Merge "Don't override active_worst_quality in 2 pass"
Johann [Fri, 6 May 2011 15:54:14 +0000 (08:54 -0700)]
Merge "neon fast quantizer updated"
John Koleszar [Fri, 6 May 2011 15:48:50 +0000 (11:48 -0400)]
Don't override active_worst_quality in 2 pass
Commit db5057c introduced a bug in that the active_worst_quality
selected by the 2 pass rate controller was being overridden for key
frames, causing a severe quality loss.
Change-Id: I4865a6fbe3e94e9b4fb9271c7dd68b455d7b371d
John Koleszar [Thu, 5 May 2011 14:53:24 +0000 (10:53 -0400)]
Use stdint.h for VS2010
VS2010 has included stdint.h, but not inttypes.h. Prefer the compiler's
version of these types. Fixes issue 327.
Change-Id: Ica71600e06b8e94e3bbb4f12988b4a9817d5e5e4
Tero Rintaluoma [Mon, 11 Apr 2011 09:04:17 +0000 (12:04 +0300)]
neon fast quantizer updated
vp8_fast_quantize_b_neon function updated and further optimized.
- match current C implementation of fast quantizer
- updated to use asm_enc_offsets for structure members
- updated ads2gas scripts to handle alignment issues
Change-Id: I5cbad9c460ad8ddb35d2970a8684cc620711c56d
Aron Rosenberg [Fri, 6 May 2011 04:10:37 +0000 (00:10 -0400)]
Fix semaphore emulation on Windows
The existing emulation of posix semaphores on Windows uses SetEvent()
and WaitForSingleObject(), which implements a binary semaphore, not a
counting semaphore as implemented by posix. This causes deadlock when
used with the expected posix semantics. Instead, this patch uses the
CreateSemaphore() and ReleaseSemaphore() calls (introduced in Windows
2000) which have the expected behavior.
This patch also reverts commit eb16f00, which split a semaphore that
was being used with counting semantics into two binary semaphores.
That commit is unnecessary with corrected emulation.
Change-Id: If400771536a27af4b0c3a31aa4c4e9ced89ce6a0
Yunqing Wang [Thu, 5 May 2011 14:42:29 +0000 (10:42 -0400)]
Fix rare hang in multi-thread encoder on Windows
This patch is to fix a rare hang in multi-thread encoder that was
only seen on Windows. Thanks for John's help in debugging the
problem. More test is needed.
Change-Id: Idb11c6d344c2082362a032b34c5a602a1eea62fc
Johann [Thu, 5 May 2011 13:16:21 +0000 (06:16 -0700)]
Merge "Loopfilter NEON: Use VMOV for constant vectors instead of VLD."
Yunqing Wang [Thu, 5 May 2011 11:59:54 +0000 (04:59 -0700)]
Merge "Runtime detection of available processor cores."
Attila Nagy [Wed, 4 May 2011 07:51:26 +0000 (10:51 +0300)]
Loopfilter NEON: Use VMOV for constant vectors instead of VLD.
Change-Id: I562b6e01c32bb51d00f3b95faf757fc7dc29a3a3
Yunqing Wang [Tue, 3 May 2011 18:59:32 +0000 (11:59 -0700)]
Merge "Modify HEX search"
Yunqing Wang [Mon, 2 May 2011 17:21:59 +0000 (13:21 -0400)]
Modify HEX search
Changed 8-neighbor searching to 4-neighour searching, and continued
searching until the center point is the best match.
Test on test set showed 1.3% encoding speed improvement as well as
0.1% PSNR and SSIM improvement at speed=-5 (rt mode).
Will continue to improve it.
Change-Id: If4993b1907dd742b906fd3f86fee77cc5932ee9a
Yaowu Xu [Tue, 3 May 2011 18:20:52 +0000 (11:20 -0700)]
Merge "change to use fast ssim code for internal ssim calculations"
Yaowu Xu [Mon, 2 May 2011 22:27:14 +0000 (15:27 -0700)]
change to use fast ssim code for internal ssim calculations
The commit also removed the slow ssim calculation that uses a 7x7
kernel, and revised the comments to better describe how sample ssim
values are computed and averaged
Change-Id: I1d874073cddca00f3c997f4b9a9a3db0aa212276
Ronald S. Bultje [Mon, 2 May 2011 17:56:41 +0000 (13:56 -0400)]
build: change LDFLAGS/CFLAGS ordering.
Always use CFLAGS/LDFLAGS that point to headers and libvpx.a inside our
build tree before ones from the environment, which could reference
headers or libs outside the build tree.
This fixes issue 307.
Change-Id: I34d176b8c21098f6da5ea71f0147d3c49283cc45
John Koleszar [Mon, 2 May 2011 13:50:22 +0000 (06:50 -0700)]
Merge "Fix documentation typos"
John Koleszar [Mon, 2 May 2011 13:28:37 +0000 (09:28 -0400)]
Fix compile error with --enable-postproc-visualizer
Typo.
Change-Id: I9cc6a4587c3d93c9f0da5e101d376741fc9622a4
Thijs Vermeir [Fri, 29 Apr 2011 21:29:28 +0000 (23:29 +0200)]
Fix documentation typos
Change-Id: I97124670926433bf1593c91660d8b8f8482ea9ce
Ronald S. Bultje [Fri, 29 Apr 2011 18:51:37 +0000 (11:51 -0700)]
Make hor UV predict ~2x faster (73 vs 132 cycles) using SSSE3.
Change-Id: I658a1df7d825f820573cb2d11ad402f9d2791035
Yaowu Xu [Fri, 29 Apr 2011 16:37:59 +0000 (09:37 -0700)]
changed configure option name to reduce confusion
Renamed configure option "enable-psnr" to "enable-internal-stats" to
better reflect the purpose of the option and eliminate the confusion
reported in http://code.google.com/p/webm/issues/detail?id=35
Change-Id: If72df6fdb9f1e33dab1329240ba4d8911d2f1f7a
Yunqing Wang [Fri, 29 Apr 2011 15:27:58 +0000 (08:27 -0700)]
Merge "Use insertion sort instead of quick sort"
Scott LaVarnway [Fri, 29 Apr 2011 14:13:49 +0000 (07:13 -0700)]
Merge "Consolidated build inter predictors"
James Berry [Thu, 28 Apr 2011 19:12:00 +0000 (15:12 -0400)]
bug fix removed inline from recon_wrapper_sse2.c
removed inline from recon_wrapper_sse2.c to build
for visual stuido
Change-Id: I74a3482950448e2cdb30e9cd7087145b440d8a22
James Berry [Thu, 28 Apr 2011 18:11:32 +0000 (14:11 -0400)]
bug fix 32 bit matches 64 bit
included vpx_config.h in vpx_encoder.c
to properly define FLOATING_POINT_INIT()
Change-Id: Ie518bf5c087622658e37fca90aa4ddfe79d053f6
Scott LaVarnway [Thu, 28 Apr 2011 14:58:20 +0000 (07:58 -0700)]
Merge "Use psadbw to get the sum of bytes in a line."
Scott LaVarnway [Thu, 28 Apr 2011 14:53:59 +0000 (10:53 -0400)]
Consolidated build inter predictors
Code cleanup.
Change-Id: Ic8b0167851116c64ddf08e8a3d302fb09ab61146
Ronald S. Bultje [Wed, 27 Apr 2011 20:49:21 +0000 (13:49 -0700)]
Use psadbw to get the sum of bytes in a line.
Thanks Jason for pointing that out on #vp8. ;-).
Change-Id: I5330a753e752a8704b78a409597472628e0b26a5
Scott LaVarnway [Wed, 27 Apr 2011 19:25:32 +0000 (15:25 -0400)]
Removed unused code in reconinter
The skip flag is never set by the encoder for SPLITMV.
Change-Id: I5ae6457edb3a1193cb5b05a6d61772c13b1dc506
John Koleszar [Wed, 27 Apr 2011 19:02:55 +0000 (12:02 -0700)]
Merge "SSE2/SSSE3 optimizations for build_predictors_mbuv{,_s}()."
Ronald S. Bultje [Wed, 27 Apr 2011 17:05:10 +0000 (10:05 -0700)]
SSE2/SSSE3 optimizations for build_predictors_mbuv{,_s}().
decoding
before
10.425
10.432
10.423
=10.426
after:
10.405
10.416
10.398
=10.406, 0.2% faster
encoding
before
14.252
14.331
14.250
14.223
14.241
14.220
14.221
=14.248
after
14.095
14.090
14.085
14.095
14.064
14.081
14.089
=14.086, 1.1% faster
Change-Id: I483d3d8f0deda8ad434cea76e16028380722aee2