The main loop processes 8 bytes in 5 instructions.
For comparison, the optimal plain strnlen() requires 4 instructions per
byte (6.4x worse): LBU; ADDI; BEQZ; BNE. The current libavcodec C code
involves 5 instructions per byte (8x worse). Actual benchmarks may be
slightly less favourable due to latency from ORC.B to BNE.
This performs the start code search which was previously part of
h264_find_frame_end() - the most CPU intensive part of the function.
By itself, this results in a performance regression:
Before After
Mean StdDev Mean StdDev Change
Overall time 2925.6 26.2 3068.5 31.7 -4.7%
but this can more than be made up for by platform-optimised
implementations of the function.
Signed-off-by: Martin Storsjö <martin@martin.st>
The non-intra-pcm branch in hl_decode_mb (simple, 8bpp) goes from 700
to 672 cycles, and the complete loop of decode_mb_cabac and hl_decode_mb
(in the decode_slice loop) goes from 1759 to 1733 cycles on the clip
tested (cathedral), i.e. almost 30 cycles per mb faster.
Signed-off-by: Martin Storsjö <martin@martin.st>
These functions are mostly H264-specific (the only other user I can
spot is bink), and this allows us to special-case some functionality
for H264. Also remove the 16-bit-coeff with >8bpp versions (unused)
and merge the duplicate 32-bit-coeff for >8bpp (identical).
Signed-off-by: Martin Storsjö <martin@martin.st>
The non-intra-pcm branch in hl_decode_mb (simple, 8bpp) goes from 700
to 672 cycles, and the complete loop of decode_mb_cabac and hl_decode_mb
(in the decode_slice loop) goes from 1759 to 1733 cycles on the clip
tested (cathedral), i.e. almost 30 cycles per mb faster.
Signed-off-by: Michael Niedermayer <michaelni@gmx.at>
These functions are mostly H264-specific (the only other user I can
spot is bink), and this allows us to special-case some functionality
for H264. Also remove the 16-bit-coeff with >8bpp versions (unused)
and merge the duplicate 32-bit-coeff for >8bpp (identical).
Signed-off-by: Michael Niedermayer <michaelni@gmx.at>
This patch lets e.g. dsputil_init chose dsp functions with respect to
the bit depth to decode. The naming scheme of bit depth dependent
functions is <base name>_<bit depth>[_<prefix>] (i.e. the old
clear_blocks_c is now named clear_blocks_8_c).
Note: Some of the functions for high bit depth is not dependent on the
bit depth, but only on the pixel size. This leaves some room for
optimizing binary size.
Preparatory patch for high bit depth h264 decoding support.
Signed-off-by: Ronald S. Bultje <rsbultje@gmail.com>
This patch lets e.g. dsputil_init chose dsp functions with respect to
the bit depth to decode. The naming scheme of bit depth dependent
functions is <base name>_<bit depth>[_<prefix>] (i.e. the old
clear_blocks_c is now named clear_blocks_8_c).
Note: Some of the functions for high bit depth is not dependent on the
bit depth, but only on the pixel size. This leaves some room for
optimizing binary size.
Preparatory patch for high bit depth h264 decoding support.
Signed-off-by: Michael Niedermayer <michaelni@gmx.at>
No speed improvement, but necessary for some future stuff.
Also opens up the possibility of asm chroma dc idct/dequant.
Originally committed as revision 26349 to svn://svn.ffmpeg.org/ffmpeg/trunk
Since we no longer have non-transposed scantables, the problem it warns about
no longer exists.
Originally committed as revision 26339 to svn://svn.ffmpeg.org/ffmpeg/trunk
About 2.5x the speed.
NOTE: the way that the asm code handles large qmuls is a bit suboptimal.
If x264-style dequant was used (separate shift and qmul values), it might
be possible to get some extra speed.
Originally committed as revision 26336 to svn://svn.ffmpeg.org/ffmpeg/trunk
Passing an explicit filename to this command is only necessary if the
documentation in the @file block refers to a file different from the
one the block resides in.
Originally committed as revision 22921 to svn://svn.ffmpeg.org/ffmpeg/trunk
This moves the H264-specific functions from DSPContext to the new
H264DSPContext. The code is made conditional on CONFIG_H264DSP
which is set by the codecs requiring it.
The qpel and chroma MC functions are not moved as these are used by
non-h264 code.
Originally committed as revision 22565 to svn://svn.ffmpeg.org/ffmpeg/trunk
Rémi Denis-Courmont
gxw
Andreas Rheinhardt
James Almer
Michael Niedermayer
Vittorio Giovara
Shivraj Patil
Ben Avison
Janne Grunau
Ronald S. Bultje
Diego Biurrun
Baptiste Coudurier
Jason Garrett-Glaser
Daniel Kang
Oskar Arvidsson
Mans Rullgard
Jason Garrett-Glaser