ffmpeg/doc/optimization.txt

158 lines
5.0 KiB
Plaintext

optimization Tips (for libavcodec):
What to optimize:
if u plan to do non-x86 architecture specific optimiztions (SIMD normally) then
take a look in the i386/ directory, as most important functions are allready
optimized for MMX
if u want to do x86 optimizations then u can either try to finetune the stuff in the
i386 directory or find some other functions in the c source to optimize, but there
arent many left
Understanding these overoptimized functions:
as many functions, like the c ones tend to be a bit unreadable currently becouse
of optimizations it is difficult to understand them (and write arichtecture
specific versions, or optimize the c functions further) it is recommanded to look
at older CVS versions of the interresting files (just use CVSWEB at
(http://cvs.sourceforge.net/cgi-bin/viewcvs.cgi/ffmpeg/ffmpeg/libavcodec/))
or perhaps look into the other architecture specific versions in i386/, ppc/,
alpha/, ...; even if u dont understand the instructions exactly it could help
understanding the functions & how they can be optimized
NOTE:!!! if u still dont understand some function then ask at our mailing list!!!
(http://lists.sourceforge.net/lists/listinfo/ffmpeg-devel)
wtf is that function good for ....:
the primary purpose of that list is to avoid wasting time to optimize functions
which are rarely used
put(_no_rnd)_pixels{,_x2,_y2,_xy2}
used in motion compensation (en/decoding)
avg_pixels{,_x2,_y2,_xy2}
used in motion compensation of B Frames
these are less important then the put*pixels functions
avg_no_rnd_pixels*
unused
pix_abs16x16{,_x2,_y2,_xy2}
used in motion estimation (encoding) with SAD
pix_abs8x8{,_x2,_y2,_xy2}
used in motion estimation (encoding) with SAD of MPEG4 4MV only
these are less important then the pix_abs16x16* functions
put_mspel8_mc* / wmv2_mspel8*
used only in WMV2
it is not recommanded that u waste ur time with these, as WMV2 is a
ugly and relativly useless codec
mpeg4_qpel* / *qpel_mc*
use in MPEG4 qpel Motion compensation (encoding & decoding)
the qpel8 functions are used only for 4mv
the avg_* functions are used only for b frames
optimizing them should have a significant impact on qpel encoding & decoding
qpel{8,16}_mc??_old_c / *pixels{8,16}_l4
just used to workaround a bug in old libavcodec encoder
dont optimze them
tpel_mc_func {put,avg}_tpel_pixels_tab
used only for SVQ3, so only optimze them if u need fast SVQ3 decoding
add_bytes/diff_bytes
for huffyuv only, optimize if u want a faster ff-huffyuv codec
get_pixels / diff_pixels
used for encoding, easy
clear_blocks
easiest, to optimize
gmc
used for mpeg4 gmc
optimizing this should have a significant effect on the gmc decoding speed but
its very likely impossible to write in SIMD
gmc1
used for chroma blocks in mpeg4 gmc with 1 warp point
(there are 4 luma & 2 chroma blocks per macrobock, so
only 1/3 of the gmc blocks use this, the other 2/3
use the normal put_pixel* code, but only if there is
just 1 warp point)
Note: Divx5 gmc always uses just 1 warp point
pix_sum
used for encoding
hadamard8_diff / sse / sad == pix_norm1 / dct_sad / quant_psnr / rd / bit
specific compare functions used in encoding, it depends upon the command line
switches which of these are used
dont waste ur time with dct_sad & quant_psnr they arent really usefull
put_pixels_clamped / add_pixels_clamped
used for en/decoding in the IDCT, easy
Note, some optimized IDCTs have the add/put clamped code included and then
put_pixels_clamped / add_pixels_clamped will be unused
idct/fdct
idct (encoding & decoding)
fdct (encoding)
difficult to optimize
dct_quantize_trellis
used for encoding with trellis quantization
difficult to optimize
dct_quantize
used for encoding
dct_unquantize_mpeg1
used in mpeg1 en/decoding
dct_unquantize_mpeg2
used in mpeg2 en/decoding
dct_unquantize_h263
used in mpeg4/h263 en/decoding
FIXME remaining functions?
btw, most of these are in dsputil.c/.h some are in mpegvideo.c/.h
Alignment:
some instructions on some architectures have strict alignment restrictions,
for example most SSE/SSE2 inctructios on X86
the minimum guranteed alignment is writen in the .h files
for example:
void (*put_pixels_clamped)(const DCTELEM *block/*align 16*/, UINT8 *pixels/*align 8*/, int line_size);
Links:
http://www.aggregate.org/MAGIC/
X86 specific:
http://developer.intel.com/design/pentium4/manuals/248966.htm
The IA-32 Intel Architecture Software Developer's Manual, Volume 2:
Instruction Set Reference
http://developer.intel.com/design/pentium4/manuals/245471.htm
http://www.agner.org/assem/
AMD Athlon Processor x86 Code Optimization Guide:
http://www.amd.com/us-en/assets/content_type/white_papers_and_tech_docs/22007.pdf
GCC asm links:
official doc but quite ugly
http://gcc.gnu.org/onlinedocs/gcc/Extended-Asm.html
a bit old (note "+" is valid for input-output, even though the next says its not)
http://www.cs.virginia.edu/~clc5q/gcc-inline-asm.pdf