GitLab

Enable with --constrained-intra.  Significantly reduces compression, but required for the base layer of SVC encodes and maybe some other use-cases.

Commit sponsored by a media streaming company that wishes to remain anonymous.

Avoid unnecessary cond_wait

Also eliminate some NANs in stat output with intra-only encoding.
Marginal speedup: disable stat calculation if log level is below X264_LOG_INFO.
Various minor cosmetics.

libx264 now returns NAL units instead of raw data.  x264_nal_encode is no longer a public function.
See x264.h for full documentation of changes.
New parameter: b_annexb, on by default.  If disabled, startcodes are replaced by sizes as in mp4.
x264's VBV now works on a NAL level, taking into account escape codes.
VBV will also take into account the bit cost of SPS/PPS, but only if b_repeat_headers is set.
Add an overhead tracking system to VBV to better predict the constant overhead of frames (headers, NALU overhead, etc).

Fixes some extremely rare threading race conditions and makes the code cleaner.
Downside: slightly higher memory usage when calling multiple encoders from the same application.

Move lookahead into a separate thread, set to higher priority than the other threads, for optimal performance.
Reduces the amount that lookahead bottlenecks encoding, greatly increasing performance with lookahead-intensive settings (e.g. b-adapt 2) on many-core CPUs.
Buffer size can be controlled with --sync-lookahead, which defaults to auto (threads+bframes buffer size).
Note that this buffer is separate from the rc-lookahead value.
Note also that this does not split lookahead itself into multiple threads yet; this may be added in the future.
Additionally, split frames into "fdec" and "fenc" frame types and keep the two separate.
This split greatly reduces memory usage, which helps compensate for the larger lookahead size.
Extremely special thanks to Michael Kazmier and Alex Giladi of Avail Media, the original authors of this patch.

Slicing support is available through three methods (which can be mixed):
--slices sets a number of slices per frame and ensures rectangular slices (required for Blu-ray).  Overridden by either of the following options:
--slice-max-mbs sets a maximum number of macroblocks per slice.
--slice-max-size sets a maximum slice size, in bytes (includes NAL overhead).
Implement macroblock re-encoding support to allow highly accurate slice size limitation.  Might be useful for other things in the future, too.

Avoid an int->float conversion with a small table.
Change lowres_inter_types to a bitfield; cut its size by 75%.
Somewhat lower memory usage with lots of bframes.
Make log2/exp2 tables global to avoid duplication.

22->13 cycles on Core 2 with mfpmath=sse

Neither GCC nor ARMCC support 16 byte stack alignment despite the fact that NEON loads require it.
These macros only work for arrays, but fortunately that covers almost all instances of stack alignment in x264.

Fuzz tests show that all mallocs appear to be checked correctly now.

On by default; can be turned off with --no-mbtree.
Uses a large lookahead to track temporal propagation of data and weight quality accordingly.
Requires a very large separate statsfile (2 bytes per macroblock) in multi-pass mode.
Doesn't work with b-pyramid yet.
Note that MB-tree inherently measures quality different from the standard qcomp method, so bitrates produced by CRF may change somewhat.
This makes the "medium" preset a bit slower.  Accordingly, make "fast" slower as well, and introduce a new preset "faster" between "fast" and "veryfast".
All presets "fast" and above will have MB-tree on.
Add a new option, --rc-lookahead, to control the distance MB tree looks ahead to perform propagation analysis.
Default is 40; larger values will be slower and require more memory but give more accurate results.
This value will be used in the future to control ratecontrol lookahead (VBV).
Add a new option, --no-psy, to disable all psy optimizations that don't improve PSNR or SSIM.
This disables psy-RD/trellis, but also other more subtle internal psy optimizations that can't be controlled directly via external parameters.
Quality improvement from MB-tree is about 2-70% depending on content.
Strength of MB-tree adjustments can be tweaked using qcompress; higher values mean lower MB-tree strength.
Note that MB-tree may perform slightly suboptimally on fades; this will be fixed by weighted prediction, which is coming soon.

Refactor trellis lambda selection to be done in analyse_init instead of in trellis.
This will allow for more easy adaption of lambda later on; for now it allows constant lambda across variable QPs.
QPRD is only available with adaptive quantization enabled and generally improves SSIM and visual quality.
Additionally, weight the SSD values from RD based on the relative QP offset for chroma; helps visually at high QPs where chroma has a lower QP than luma.
This fixes some visual artifacts created by QPRD at high QPs.
Note that this generally hurts PSNR and SSIM, and so is only on when psy-RD is on.

Faster CABAC mvd coding.

This measures the total percentage of blocks, intra and inter, which have nonzero coefficients.
"y,uvAC,uvDC" refers to luma, chroma DC, and chroma AC blocks.
Note that skip blocks are included in this stat.

Add support for no-b-adapt + pre-scenecut (patch by BugMaster)
Pre-scenecut was generally better than regular scenecut in terms of accuracy and regular scenecut didn't work in threaded mode anyways.
Add no-scenecut option (scenecut=0 is now no scenecut; previously it was -1)
Fix an incorrect bias towards P-frames near scenecuts with B-adapt 2.
Simplify pre-scenecut code.

r1105 introduced array overflow in cbp handling

Assembly versions of most remaining 4x4 and 8x8 intra pred functions.
Assembly version of predict_8x8_filter.
A few other optimizations.
Primarily Core 2-optimized.

Modify quantization to also calculate array_non_zero.
PPC assembly changes by gpoirior.
New quant asm includes some small tweaks to quant and SSE4 versions using ptest for the array_non_zero.
Use this new feature of quant to merge nnz/cbp calculation directly with encoding and avoid many unnecessary calls to dequant/zigzag/decimate/etc.
Also add new i16x16 DC-only iDCT with asm.
Since intra encoding now directly calculates nnz, skip_intra now backs up nnz/cbp as well.
Output should be equivalent except when using p4x4+RDO because of a subtlety involving old nnz values lying around.
Performance increase in macroblock_encode: ~18% with dct-decimate, 30% without at CRF 25.
Overall performance increase 0-6% depending on encoding settings.

The benefit in the most extreme contrived situation was at most 0.001db PSNR, at the cost of slower decoding.
As this option was basically useless, it was a waste of code and prevented some other useful optimizations.
Remove some unused mc code related to sub-8x8 partitions.
Small deblocking speedup when p4x4 is used.
Also remove unused x264_nal_decode prototype from x264.h.

there should now be no memory allocation outside of init-time.

reduce memory if using ESA and not p4x4

Use a VLC table for common levelcodes instead of constructing them on-the-spot
Branchless version of i_trailing calculation (2x faster on Nehalem)
Completely remove array_non_zero_count and instead use the count calculated in level/run coding.  Note: this slightly changes output with subme > 7 due to different nonzero counts being stored during qpel RD.

Early-terminate in residual writing using stored nnz counts
To allow the above, store nnz counts for luma and chroma DC
Add assembly functions to find the last nonzero coefficient in a block
Overall ~1.9% faster at subme9+8x8dct+qp25 with CAVLC, ~0.7% faster with CABAC
Note this changes output slightly with CABAC RDO because it requires always storing correct nnz values during RDO, which wasn't done before in cases it wasn't useful.
CAVLC output should be equivalent.

This improves lossless compression by about 4-25% depending on source.
The benefit is generally higher for intra-only compression.
Also add support for 8x8dct and i8x8 blocks in lossless mode; this improves compression very slightly.
In some rare cases 8x8dct can hurt compression in lossless mode, but its usually helpful, albeit marginally.
Note that 8x8dct is only available with CABAC as it is never useful with CAVLC.
High 4:4:4 Predictive replaced the previous profile in a 2007 revision to the H.264 standard.
The only known compliant decoder for this profile is the latest version of CoreAVC.
As I write this, JM does not actually correctly decode this profile.
Hopefully this lack of support will soon change with this commit, as x264 will be (to my knowledge) the first compliant encoder.

The latter, psy-trellis, is disabled by default and is reserved as experimental; your mileage may vary.
Default subme is raised to 6 so that psy RD is on by default.

This method (--b-adapt 2) uses a Viterbi algorithm somewhat similar to that used in trellis quantization.
Note that it is not fully optimized and is very slow with large --bframes values.
It also takes into account weightb, which should improve fade detection.
Additionally, changes were made to cache lowres intra results for each frame to avoid recalculating them.  This should improve performance in both B-frame decision methods.
This can also be done for motion vectors, which will dramatically improve b-adapt 2 performance when it is complete.
This patch also reads b_adapt and scenecut settings from the first pass so that the x264 header information in the output file will have correct information (since frametype decision is only done on the first pass).

(changes 2pass statsfile format)

Also remove display of "PCM" if PCM mode is never used in the encode.
L1 reflist information will only show if pyramid coding is used.

In RD mode, always consider PCM as a macroblock mode possibility
Fix bitstream writing for PCM blocks in CAVLC and CABAC, and a few other minor changes to make PCM work.
PCM macroblocks improve compression at very low QPs (1-5) and in lossless mode.

Update AUTHORS file with Gabriel and me
update XCHG macro to work correctly in if statements
Add new lookup tables for block_idx and fdec/fenc addresses
Slightly faster array_non_zero_count_mmx (patch by holger)
Eliminate branch in analyse_intra
Unroll loops in and clean up chroma encode
Convert some for loops to do/while loops for speed improvement
Do explicit write-combining on --me tesa mvsad_t struct
Shrink --me esa zero[] array
Speed up bime by reducing size of visited[][][] array

Update "Authors" lists based on actual authorship; highest is most important
Update copyright notices and remove old CVS tags from file headers
Add file headers to GTK and other sections missing them
Update FSF address
Other header-related cosmetics

Converting NNZ to raster order simplifies a lot of the load/store code and allows more use of write-combining.
More use of write-combining throughout load/save code in common/macroblock.c
GCC has aliasing issues in the case of stores to 8-bit heap-allocated arrays; dereferencing the pointer once avoids this problem and significantly increases performance.
More manual loop unrolling and such.
Move all packXtoY functions to macroblock.h so any function can use them.
Add pack8to32.
Minor optimizations to encoder/macroblock.c

x264 will now terminate gracefully rather than SIGILL when run on a machine with no MMXEXT support.
A configure option is now available to build x264 without assembly support for support on such old CPUs as the Pentium 2, K6, etc.