This is after discussion with the hardware team. Update the unit test
to take these sizes into account. Split out some duplicate code into
a separate file so it can be shared.
Implement convolve8_avg using common functions which are already optimized
instead of using more obscure ones which have only C versions. Encoder
overall speed-up of about 12%.
Jingning Han [Sat, 9 Feb 2013 00:19:42 +0000 (16:19 -0800)]
butterfly inverse 4x4 ADST
fixed format issues.
Implement the inverse 4x4 ADST using 9 multiplications. For this
particular dimension, the original ADST transform can be
factorized into simpler operations, hence is retained.
Scott LaVarnway [Sat, 9 Feb 2013 23:15:14 +0000 (15:15 -0800)]
Bug fix: ssse3 version of subpixel did not match C code
A 16 bit overflow condition occurs when using the EIGHTTAP_SMOOTH filters.
(vp9_sub_pel_filters_8lp) Changed the order of the adds to fix this problem.
Also added ssse3 support for 4x4 subpixel filtering.
Also port the 4x4, 16x16, 8x16 and 16x8 versions to x86inc.asm; this
makes them all slightly faster, particularly on x86-64. Remove SSE3
sad16x16 version, since the SSE2 version is now faster.
Cache the constant offset in one variable to prevent re-loading that
in each loop iteration, and mark the function as inline so we can use
the fact that the transform size is always known in the caller.
John Koleszar [Thu, 7 Feb 2013 18:09:05 +0000 (10:09 -0800)]
Pass macroblock index to pick inter functions
Pass the current mb row and column around rather than the
recon_yoffset and recon_uvoffset, since those offsets will
change from predictor to predictor, based on the reference
frame selection.
John Koleszar [Fri, 8 Feb 2013 22:20:05 +0000 (14:20 -0800)]
Merge changes Icd1a2a5a,I204d17a1,I3ed92117 into experimental
* changes:
Initial support for resolution changes on P-frames
Avoid allocating memory when resizing frames
Adds a test for the VP8E_SET_SCALEMODE control
John Koleszar [Wed, 6 Feb 2013 23:54:52 +0000 (15:54 -0800)]
Initial support for resolution changes on P-frames
Allows inter-frames to change resolution. Currently these are
almost equivalent to keyframes, as only intra prediction modes
are allowed, but without the other context resets that occur on
keyframes.
John Koleszar [Wed, 6 Feb 2013 22:22:17 +0000 (14:22 -0800)]
Avoid allocating memory when resizing frames
As long as the new frame is smaller than the size that was originally
allocated, we don't need to free and reallocate the memory allocated.
Instead, do the allocation on the size of the first frame. We could
make this passed in from the application instead, if we wanted to
support external upscaling.
John Koleszar [Wed, 6 Feb 2013 20:44:20 +0000 (12:44 -0800)]
Adds a test for the VP8E_SET_SCALEMODE control
Tests that the external interface to set the internal codec scaling
works as expected. Also updates the test to pull the height from
the decoded frame size rather than parsing the keyframe header,
in anticipation of allowing resolution changes on non-keyframes.
John Koleszar [Fri, 8 Feb 2013 01:00:37 +0000 (17:00 -0800)]
Restore SSSE3 subpixel filters in new convolve framework
This commit adds the 8 tap SSSE3 subpixel filters back into the code
underneath the convolve API. The C code is still called for 4x4
blocks, as well as compound prediction modes. This restores the
encode performance to be within about 8% of the baseline.
Paul Wilkins [Wed, 6 Feb 2013 13:02:53 +0000 (13:02 +0000)]
Nearest / Zero Mv default entropy tweak.
Tweak to default mode context to account for the fact
that when there are no non zero motion candidates
Nearest is now the preferred mode for coding a 0,0
vector.
Jingning Han [Tue, 5 Feb 2013 20:37:13 +0000 (12:37 -0800)]
Butterfly ADST based hybrid transform
Refactor the 8x8 inverse hybrid transform. It is now consistent
with the new inverse DCT. Overall performance loss (due to the
use of this variant ADST, and the rounding errors in the butterfly
implementation) for std-hd is -0.02.
Fixed BUILD warning.
Devise a variant of the original ADST, which allows butterfly
computation structure. This new transform has kernel of the
form: sin((2k+1)*(2n+1) / (4N)). One of its butterfly structures
using floating-point multiplications was reported in Z. Wang,
"Fast algorithms for the discrete W transform and for the discrete
Fourier transform", IEEE Trans. on ASSP, 1984.
This patch includes the butterfly implementation of the inverse
ADST/DCT hybrid transform of dimension 8x8.
Paul Wilkins [Tue, 5 Feb 2013 12:54:09 +0000 (12:54 +0000)]
Added skip switches for SB32 and SB64
Added switches and code to skip/breakout from
doing SB32 and SB64 tests based on whether
the 16x16 MB tests used split modes. Also to
optionally skip 64x64 if 16x16 was chosen over
32x32.
Impact varies depending on clip from a few %
up to almost 50% on encode speed. Only the
split mode breakout is currently enabled.
This patch adds column-based tiling. The idea is to make each tile
independently decodable (after reading the common frame header) and
also independendly encodable (minus within-frame cost adjustments in
the RD loop) to speed-up hardware & software en/decoders if they used
multi-threading. Column-based tiling has the added advantage (over
other tiling methods) that it minimizes realtime use-case latency,
since all threads can start encoding data as soon as the first SB-row
worth of data is available to the encoder.
There is some test code that does random tile ordering in the decoder,
to confirm that each tile is indeed independently decodable from other
tiles in the same frame. At tile edges, all contexts assume default
values (i.e. 0, 0 motion vector, no coefficients, DC intra4x4 mode),
and motion vector search and ordering do not cross tiles in the same
frame.
t log
Tile independence is not maintained between frames ATM, i.e. tile 0 of
frame 1 is free to use motion vectors that point into any tile of frame
0. We support 1 (i.e. no tiling), 2 or 4 column-tiles.
The loopfilter crosses tile boundaries. I discussed this briefly with Aki
and he says that's OK. An in-loop loopfilter would need to do some sync
between tile threads, but that shouldn't be a big issue.
Resuls: with tiling disabled, we go up slightly because of improved edge
use in the intra4x4 prediction. With 2 tiles, we lose about ~1% on derf,
~0.35% on HD and ~0.55% on STD/HD. With 4 tiles, we lose another ~1.5%
on derf ~0.77% on HD and ~0.85% on STD/HD. Most of this loss is
concentrated in the low-bitrate end of clips, and most of it is because
of the loss of edges at tile boundaries and the resulting loss of intra
predictors.
TODO:
- more tiles (perhaps allow row-based tiling also, and max. 8 tiles)?
- maybe optionally (for EC purposes), motion vectors themselves
should not cross tile edges, or we should emulate such borders as
if they were off-frame, to limit error propagation to within one
tile only. This doesn't have to be the default behaviour but could
be an optional bitstream flag.
John Koleszar [Tue, 29 Jan 2013 00:59:03 +0000 (16:59 -0800)]
Convert subpixel filters to use convolve framework
Update the code to call the new convolution functions to do subpixel
prediction rather than the existing functions. Remove the old C and
assembly code, since it is unused. This causes a 50% performance
reduction on the decoder, but that will be resolved when the asm for
the new functions is available.
There is no consensus for whether 6-tap or 2-tap predictors will be
supported in the final codec, so these filters are implemented in
terms of the 8-tap code, so that quality testing of these modes
can continue. Implementing the lower complexity algorithms is a
simple exercise, should it be necessary.
This code produces slightly better results in the EIGHTTAP_SMOOTH
case, since the filter is now applied in only one direction when
the subpel motion is only in one direction. Like the previous code,
the filtering is skipped entirely on full-pel MVs. This combination
seems to give the best quality gains, but this may be indicative of a
bug in the encoder's filter selection, since the encoder could
achieve the result of skipping the filtering on full-pel by selecting
one of the other filters. This should be revisited.
Quality gains on derf positive on almost all clips. The only clip
that seemed to be hurt at all datarates was football
(-0.115% PSNR average, -0.587% min). Overall averages 0.375% PSNR,
0.347% SSIM.
John Koleszar [Fri, 25 Jan 2013 17:47:09 +0000 (09:47 -0800)]
Add 8-tap generic convolver
This commit introduces a new convolution function which will be used to
replace the existing subpixel interpolation functions. It is much the
same as the existing functions, but allows for changing the filter
kernel on a per-pixel basis, and doesn't bake in knowledge of the
filter to be applied or the size of the resulting block into the
function name.
Replacing the existing subpel filters will come in a later commit.
Paul Wilkins [Tue, 5 Feb 2013 10:28:26 +0000 (10:28 +0000)]
Change definition of NearestMV.
This commit makes the NearestMV match the chosen
best reference MV. It can be a 0,0 or non zero vector
which means the the compound nearest mv mode can
combine a 0,0 and a non zero vector.
Scott LaVarnway [Tue, 5 Feb 2013 00:49:17 +0000 (16:49 -0800)]
Added vp9_short_idct1_32x32_c
and called this function in vp9_dequant_idct_add_32x32_c when
eob == 1. For the test clip used, the decoder performance improved
by 21+%. Based on Yaowu's 16 point idct work.
Yaowu Xu [Fri, 1 Feb 2013 00:16:28 +0000 (16:16 -0800)]
Changes 16 point idct
This commit changes the inverse 16 point dct to use the same algorithm
as the one for 32 point idct. In fact, now 16 point dct uses the exact
version of the souce code for even portion of the 32 point idct.
Tests showed current implementation has significant better accuracy
than the previous version. With this implementation and the minor bug
fix on forward 16 point dct, encoding tests showed about 0.2% better
compression of CIF set, test results on std-hd setting pending.
Yaowu Xu [Wed, 30 Jan 2013 21:01:49 +0000 (13:01 -0800)]
A fix point implementation of 32x32 idct
This commit changes the 32x32 idct to use integer only. The algorithm
was taken directly from "A Fast Computational Algorithm for the
Discrete Cosine Tranform" by W. Chen, et al., which was published in
IEEE Transaction on Communication Vol. Com.-25 No. 9, 1977. The signal
flow graph in the original paper is for a 32 point forward dct, the
current implementation of inverse DCT was done by follow the graph in
reversed direction.
With this implementation, the 32 point inverse dct contains a 16 point
inverse dct in its even portion, similarly the 16 point idct further
contains 8 point and 4 point inverse dcts.
As of patch 4, encoding tests showed there is no compression loss when
compared against the floating point baseline. Numbers even showed very
small postives. (cif: .01%, std-hd: .05%).
Ronald S. Bultje [Wed, 30 Jan 2013 05:46:31 +0000 (21:46 -0800)]
Default superblock skip flag to 32x32 for skip-blocks.
This is identical to the later decisions made in encode_superblock().
This commit doesn't actually change anything, but makes the mbmi state
more consistent between the RD loop and the final encode result.
Ronald S. Bultje [Sat, 26 Jan 2013 00:08:19 +0000 (16:08 -0800)]
Fix block pointer corruption in intra8x8 prediction with 4x4 transform.
The RD loop would change the pointer after the first mode (DC) was tested,
leading to corrupt block objects being provided for the others. This
would essentially render the i8x8 predictor useless.
Paul Wilkins [Tue, 29 Jan 2013 13:33:17 +0000 (13:33 +0000)]
Remove eob_max_offset markers.
Remove eob_max_offset markers and replace
with the generic skip_block flag to indicate
to the quantizer that all coeffs to be set to 0
and eob position set to 0;
Paul Wilkins [Thu, 24 Jan 2013 18:28:33 +0000 (18:28 +0000)]
Simplify Zero bin and zero bin run code.
Simplification to eliminate a number of very large data
data structures. All zero run, zbin boosts for different
transform sizes are now limited to a maximum run length
of 15 before they max out the boost.
Some further work still needs be done to refactor, rationalize
and optimize the multiple quantizer functions.
The simplification coupled with tweaks to the 16 element array
now used for all transform sizes, has minimal effect on quality.
Deb Mukherjee [Fri, 25 Jan 2013 19:30:28 +0000 (11:30 -0800)]
Adding a frame parallel decoding mode
Adds a flag to disable features that would inhibit frame parallel
decoding. This includes backward adaptation and MV sorting based
on search in ref frame buffer.
Deb Mukherjee [Tue, 15 Jan 2013 14:43:35 +0000 (06:43 -0800)]
Adds an error-resilient mode with test
Adds an error-resilient mode where frames can be continued
to be decoded even when there are errors (due to network losses)
on a prior frame. Specifically, backward updates are turned off
and probabilities of various symbols are reset to defaults at
the beginning of each frame. Further, the last frame's mvs are
not used for the mv reference list, and the sorting of the
initial list based on search on previous frames is turned off
as well.
Also adds a test where an arbitrary set of frames are skipped
from decoding to simulate errors. The test verifies (1) that if
the error frames are droppable - i.e. frame buffer updates have
been turned off - there are no mismatch errors for the remaining
frames after the error frames; and (2) if the error-frames are non
droppable, there are not only no decoding errors but the mismatch
PSNR between the decoder's version of the post-error frames and the
encoder's version is at least 20 dB.
John Koleszar [Fri, 18 Jan 2013 19:51:12 +0000 (11:51 -0800)]
Support multiple codecs in test infrastructure
This commit starts to convert the tests to a system where the codec
to be used is provided by a factory object. Currently no tests are
instantiated for VP9 since they all fail for various reasons, but it
was verified that they're called and the correct codec is
instantiated.
projects / libvpx / log