Jerome Jiang [Thu, 5 Jan 2017 00:19:42 +0000 (16:19 -0800)]
vp9: Compute source sad for every superblock when partition copy is on.
The source sad could be used to copy the partition without going into
choose_partitioning function to speed up vp9 encoding. Computing source
sad takes little time. Speed test on Android and Linux shows little
encoding time gain (less than 1.4%).
Turned off for now since partition copy is turned off.
Jerome Jiang [Wed, 4 Jan 2017 19:22:51 +0000 (11:22 -0800)]
vp9: Set short circuit to level 3 for VGA for speed 8.
vp9: Set short circuit to level 3 for VGA for speed 8. Also change the
threshold_32x32 to 5/8*thresholds[1] to improve quality regression
caused to VGA clips.
Bug fix to avoid random crashes during ARNR filtering
The function 'vp9_find_best_sub_pixel_tree_pruned_more' is modified
to return INT_MAX for handling invalid MV cases from UINT32_MAX.
yunqingwang:
patch 3: rebased on top of the tree.
patch 4: The return type of vp9_find_best_sub_pixel_tree* was changed
to uint32_t to fix ubsan warnings. Changing UINT_MAX back to INT_MAX
was not quite right. Patch 4 modified vp9_temporal_filter.c to accept
uint32_t.
(Note: Inconsistency exists in vp9_find_best_sub_pixel_tree*, which
will be fixed in a separate CL.)
This change results in unsigned integer overflows (as reported by
-fsanitize=integer) in datarate_test.cc,
for many of --gtest_filter=VP9/DatarateOnePassCbrSvc.OnePassCbrSvc*:
unsigned integer overflow: 167198 - 185560 cannot be represented in type
'unsigned long'
As the encoder didn't change, but the input with the change to
(correctly) use Y4mVideoSource, this revert is merely masking the issue.
Gabriel Marin [Wed, 14 Dec 2016 19:07:50 +0000 (11:07 -0800)]
Remove superfluous conditional on 'shortcut'
Remove superfluous test. Produces a small improvement in instruction scheduling.
Measured a 1% to 1.5% reduction in execution time for routine vp9_optimize_b
with different compilers.
No change in behavior.
TEST=Verified that encoded files match bit for bit, with and without this
change.
BUG=b/33678225
Jerome Jiang [Mon, 19 Dec 2016 18:39:04 +0000 (10:39 -0800)]
vp9: Add feature to copy partition from the last frame.
Add feature to copy partition from the last frame.
The copy is only done under certain conditions that SAD is below threshold.
Feature is currently disabled, until threshold is tuned.
Feature will be initially used for Speed 8 (ARM).
Under extreme case of always copying partition for speed 8:
Encode time is reduced by 5.4% on rtc_derf and 7.8% on rtc.
Overall PSNR reduced by 2.1 on rtc_derf and 0.968 on rtc.
Gabriel Marin [Wed, 14 Dec 2016 00:22:48 +0000 (16:22 -0800)]
Simplify address arithmetic in vp9_optimize_b
Simplify address arithmetic on token_costs to reduce the number of generated
instructions that are used for address arithmetic inside routine
vp9_optimize_b. It also helps improve instruction scheduling depending on
compiler and optimization level.
Measured a 9.3% reduction in retired instructions and 5.3% reduction in
execution time for this routine with GCC v4.8.4 and optimization flags -O3,
and a reduction of up to 11.6% in execution time with other compilers.
No change in behavior.
TEST=Verified that encoded files match bit for bit, with and without this
change.
BUG=b/33678225
relocate the assignment to 'in' outside of the for loop. this quiets a
spurious warning in visual studio builds since: 86e340c enable vpx_idct32x32_1024_add_neon in hbd builds
Marco [Fri, 16 Dec 2016 19:15:57 +0000 (11:15 -0800)]
vp9: Change condition to enable recheck_zeromv_after_denoising.
For when denoising enabled: change condition to enable
the recheck_zeromv_after_denoising for only very high noise level.
This is causing an issue, so enabling it for very high noise
to effectively shut it off.
Johann [Fri, 16 Dec 2016 20:19:00 +0000 (12:19 -0800)]
postproc test: disable new down and across test
The new test is causing valgrind failures:
[ RUN ] SSE2/VpxPostProcDownAndAcrossMbRowTest.CheckCvsAssembly/0
==28923== Invalid read of size 16
28923== at 0x724016: ??? (deblock_sse2.asm:146)
Disable during investigation. The test is new but the code is not.
Jim Bankoski [Fri, 16 Dec 2016 16:50:55 +0000 (08:50 -0800)]
vp8 : use threading mutex's for tsan only.
To avoid decode performance hit of 2% when running on hyperthreaded
cores.
This patch only uses the mutex's when we are running tsan.
This is safe because 32 bit operations like read and store are atomic
on all the platforms we care about. Tsan warns about race situations,
but in this case either situation ( read occurs before write or write
before read) the worst case is that we go around one extra time in the
loop. So the ordering doesn't really matter.
That said a few other things have been tried :
for instance as per here:
webrtc/base/atomicops.h#52
In this patch they use:
__atomic_load_n(i, __ATOMIC_ACQUIRE);
__atomic_store_n(i, value, __ATOMIC_RELEASE);
This code works on gcc, clang ( replacing protected write and read), and
avoids tsan errors. Incurring no penalty in performance. In C11 its
replaced by straight atomic operands.
However there is no equivalent in the visual studio's we support as
int32 on all windows platforms is already atomic. To avoid tsan like
warnings on windows we'd need to use interlocked exchange and the
end result doesn't gain us any thing.
Marco [Wed, 14 Dec 2016 22:08:09 +0000 (14:08 -0800)]
vp9: Fix to usage of flag USE_ALTREF_FOR_ONE_PASS
The flag USE_ALTREF_FOR_ONE_PASS allows for alt-ref lookahead
in 1 pass vbr (from https://chromium-review.googlesource.com/#/c/365498).
This change is to make sure this macro flag only has effect if
the config flag cpi->oxcf.enable_auto_altef is also on.
No change in ytlive encoding, as USE_ALTREF_FOR_ONE_PASS is not
yet enabled.
James Zern [Thu, 8 Dec 2016 21:02:30 +0000 (13:02 -0800)]
idct16x16_add_neon: fix arm visual studio builds
after: 2d3d95f enable vpx_idct16x16_256_add_neon in hbd builds
reorder INCLUDEs and fix indent of IF/ENDIFs
remove vpx_config.asm to avoid multiple symbol definitions in windows
builds and shift idct_neon.asm.S to the top to allow use of
CONFIG_VP9_HIGHBITDEPTH in the export list.
Yunqing Wang [Wed, 7 Dec 2016 18:00:36 +0000 (10:00 -0800)]
Remove an unused first pass statistic
One of the first pass stats "new_mv_count" is no longer used in VP9,
and is removed. This also makes it easy to implement a multi-threaded
first pass. This change doesn't affect the coding performance, which
has been verified by borg tests.
Linfeng Zhang [Wed, 7 Dec 2016 19:34:00 +0000 (11:34 -0800)]
Update TEST_P(PartialIDctTest, RunQuantCheck)
1. Use correct projections when copying real dct/quant outputs.
2. Remove local random number generator and combine loops.
3. Quantization with minimum allowed step sizes instead of maximum.
This may generate larger inputs.
James Zern [Wed, 30 Nov 2016 03:47:50 +0000 (19:47 -0800)]
idct16x16,NEON: rm output_stride from pass1 fns
vpx_idct16x16_256_add_neon_pass1, vpx_idct16x16_10_add_neon:
this was a constant 8 in all cases meaning the results are stored
contiguously, this allows the number of stores to be reduced.
Marco [Mon, 5 Dec 2016 20:05:35 +0000 (12:05 -0800)]
vp9: Adjust the weight factor for segment rate cost for aq-mode=3.
Use the segment weight factor based on the target (cr->percent_refresh)
if it less than the current estimate (avergae of past usage and target).
Small improvement at low bitrates.
James Zern [Fri, 25 Nov 2016 01:51:10 +0000 (17:51 -0800)]
build/make/Android.mk: correct rtcd template var refs
the expansion of findstring and rtcd_dep_template_CONFIG_ASM_ABIS needs
to be deferred until the block is parsed as makefile syntax rather than
eval time where rtcd_dep_template_CONFIG_ASM_ABIS will be unset. this
ensures vpx_config.asm is properly created.
* changes:
Update vpx_idct4x4_16_add_neon() to pass SingleExtremeCoeff test
Refine 8-bit 4x4 idct NEON intrinsics
Add idct speed test.
Update partial_idct_test.cc to support high bitdepth
James Zern [Thu, 24 Nov 2016 00:49:19 +0000 (16:49 -0800)]
Android.mk,armv7: fix idct_neon.asm.S creation
force this to be created before any other .S files. this change
additionally removes the file from the source list as it doesn't need to
be compiled on its own.
Marco [Tue, 22 Nov 2016 00:37:32 +0000 (16:37 -0800)]
vp9: Adjust cyclic refresh parameters for low bitrates.
Increase the motion threshold and qp-delta for segment#2 boost.
This can increase the frame-drop at low bitrates, but generally
better spatial quality.
Only affects real-time mode with aq-mode=3, at very low bitrates.
Jerome Jiang [Sat, 19 Nov 2016 01:07:20 +0000 (17:07 -0800)]
Cover more filter levels in unit tests for post proc.
For some filter level, the C/MSA doesn't match SSE2. Part of unit tests
are disabled. They will be re-enabled when C/MSA funcs are fixed.
BUG=webm:1321
projects / libvpx / log