this has no immediate effect, but will allow it to be used in more codecs.

Originally committed as revision 14252 to svn://svn.ffmpeg.org/ffmpeg/trunk

2% faster vorbis on conroe, k8. 7% on celeron.

Originally committed as revision 14207 to svn://svn.ffmpeg.org/ffmpeg/trunk

Originally committed as revision 14205 to svn://svn.ffmpeg.org/ffmpeg/trunk

Originally committed as revision 14103 to svn://svn.ffmpeg.org/ffmpeg/trunk

Originally committed as revision 14081 to svn://svn.ffmpeg.org/ffmpeg/trunk

Originally committed as revision 13019 to svn://svn.ffmpeg.org/ffmpeg/trunk

Originally committed as revision 12842 to svn://svn.ffmpeg.org/ffmpeg/trunk

Originally committed as revision 12323 to svn://svn.ffmpeg.org/ffmpeg/trunk

Originally committed as revision 12318 to svn://svn.ffmpeg.org/ffmpeg/trunk

Originally committed as revision 12311 to svn://svn.ffmpeg.org/ffmpeg/trunk

Originally committed as revision 12309 to svn://svn.ffmpeg.org/ffmpeg/trunk

Originally committed as revision 12233 to svn://svn.ffmpeg.org/ffmpeg/trunk

suggested by Uoti Urpala

Originally committed as revision 12177 to svn://svn.ffmpeg.org/ffmpeg/trunk

Originally committed as revision 12166 to svn://svn.ffmpeg.org/ffmpeg/trunk

2x faster than scalar in 32bit, 4x faster in 64bit (as opposed to 8x in mmx)

Originally committed as revision 12165 to svn://svn.ffmpeg.org/ffmpeg/trunk

cycles per 1000 pixels on core2:
left: 9211->5170
top: 9283->2138
avg: 12215->7611
paeth: 64024->17360
overall rgb png decoding speed: +45%
overall greyscale png decoding speed: +6%

Originally committed as revision 12164 to svn://svn.ffmpeg.org/ffmpeg/trunk

Originally committed as revision 11732 to svn://svn.ffmpeg.org/ffmpeg/trunk

I have underestimated this a little, and these are just some ...

Originally committed as revision 11708 to svn://svn.ffmpeg.org/ffmpeg/trunk

Originally committed as revision 11296 to svn://svn.ffmpeg.org/ffmpeg/trunk

Originally committed as revision 11292 to svn://svn.ffmpeg.org/ffmpeg/trunk

Originally committed as revision 11291 to svn://svn.ffmpeg.org/ffmpeg/trunk

of array reads.

Originally committed as revision 11290 to svn://svn.ffmpeg.org/ffmpeg/trunk

array read.

Originally committed as revision 11288 to svn://svn.ffmpeg.org/ffmpeg/trunk

Originally committed as revision 11192 to svn://svn.ffmpeg.org/ffmpeg/trunk

Originally committed as revision 10983 to svn://svn.ffmpeg.org/ffmpeg/trunk

Originally committed as revision 10971 to svn://svn.ffmpeg.org/ffmpeg/trunk

4x faster than c (somehow, even though doubles only allow 2x simd).
overal flac encoding: 15-50% faster on core2, 4-11% on k8, 3-13% on p4.

Originally committed as revision 10621 to svn://svn.ffmpeg.org/ffmpeg/trunk

Originally committed as revision 10559 to svn://svn.ffmpeg.org/ffmpeg/trunk

Necessary for systems that don't align by default to 16 bytes, required by some
SSE instructions.
Requires GCC >= 4.2.
Based on patch by Gaël Chardon.

Originally committed as revision 10106 to svn://svn.ffmpeg.org/ffmpeg/trunk

Originally committed as revision 10023 to svn://svn.ffmpeg.org/ffmpeg/trunk

Originally committed as revision 9820 to svn://svn.ffmpeg.org/ffmpeg/trunk

Originally committed as revision 9785 to svn://svn.ffmpeg.org/ffmpeg/trunk

Originally committed as revision 9605 to svn://svn.ffmpeg.org/ffmpeg/trunk

Originally committed as revision 9603 to svn://svn.ffmpeg.org/ffmpeg/trunk

Originally committed as revision 9582 to svn://svn.ffmpeg.org/ffmpeg/trunk

are not compiled in.

Originally committed as revision 9581 to svn://svn.ffmpeg.org/ffmpeg/trunk

Originally committed as revision 9549 to svn://svn.ffmpeg.org/ffmpeg/trunk

Originally committed as revision 9548 to svn://svn.ffmpeg.org/ffmpeg/trunk

Originally committed as revision 9483 to svn://svn.ffmpeg.org/ffmpeg/trunk

Originally committed as revision 9332 to svn://svn.ffmpeg.org/ffmpeg/trunk

Originally committed as revision 9331 to svn://svn.ffmpeg.org/ffmpeg/trunk

Originally committed as revision 9320 to svn://svn.ffmpeg.org/ffmpeg/trunk

Originally committed as revision 9315 to svn://svn.ffmpeg.org/ffmpeg/trunk

patch by Albert Lee, trisk+xine acm.jhu edu

Originally committed as revision 9307 to svn://svn.ffmpeg.org/ffmpeg/trunk

Originally committed as revision 9291 to svn://svn.ffmpeg.org/ffmpeg/trunk

Originally committed as revision 9106 to svn://svn.ffmpeg.org/ffmpeg/trunk

Originally committed as revision 9105 to svn://svn.ffmpeg.org/ffmpeg/trunk

Originally committed as revision 9025 to svn://svn.ffmpeg.org/ffmpeg/trunk

sum_abs_dctelem_* alone:
core2: c=186 mmx2=39 sse2=21 ssse3=13 (cycles)
k8: c=163 mmx2=33 sse2=31
p4: c=370 mmx2=60 sse2=60
 dct_sad including sum_abs_dctelem_*:
core2: c=405 mmx2=258 sse2=240 ssse3=232
k8: c=624 mmx2=394 sse2=392
p4: c=849 mmx2=556 sse2=556

Originally committed as revision 9001 to svn://svn.ffmpeg.org/ffmpeg/trunk

Originally committed as revision 8559 to svn://svn.ffmpeg.org/ffmpeg/trunk