SVQ1 chroma has been special-cased aligned to 16-bytes since at least r15466
Other architectures also assume 16-byte alignment here too but set STRIDE_ALIGN
to 16.
Originally committed as revision 21736 to svn://svn.ffmpeg.org/ffmpeg/trunk
This allows to get rid of the macho64 specific hack that moves them
to rodata (with worse cache behaviour) and avoids textrels which
e.g. Gentoo does not allow for x86_64 libraries.
Originally committed as revision 21551 to svn://svn.ffmpeg.org/ffmpeg/trunk
This fixes gcc failing to fit 6 memory locations into 7 registers on x86-32
Originally committed as revision 21337 to svn://svn.ffmpeg.org/ffmpeg/trunk
causes no significant speed difference and can avoid compilation issues with
--enable-pic.
Originally committed as revision 21003 to svn://svn.ffmpeg.org/ffmpeg/trunk
29-105% faster apply_filter, 6-90% faster ape decoding on core2
(Any x86 other than core2 probably gets much less, since this is mostly due to ssse3 cachesplit avoidance and I haven't written the full gamut of other cachesplit modes.)
9-123% faster ape decoding on G4.
Originally committed as revision 20739 to svn://svn.ffmpeg.org/ffmpeg/trunk
2.2x faster than C on conroe, 3.6x on penryn.
4-6% faster huffyuv decoding if using left or plane mode and yuv
Originally committed as revision 20287 to svn://svn.ffmpeg.org/ffmpeg/trunk
corresponding dsputil functions and remove their dependency on the FLAC
encoder.
Fixes Issue1486.
Originally committed as revision 20266 to svn://svn.ffmpeg.org/ffmpeg/trunk
The src3 and step arguments to vector_fmul_add_add() are always zero
and one, respectively. This removes these arguments from the function,
simplifies the code accordingly, and renames the function to better
match the new operation.
Originally committed as revision 20061 to svn://svn.ffmpeg.org/ffmpeg/trunk
Use the new x86inc features to support 64-bit Windows on all non-x264 nasm
assembly code as well.
Patch by John Adcock, dscaler.johnad AT googlemail DOT com.
Win64 changes originally by Anton Mitrofanov.
x86util changes mostly by Holger Lubitz.
Originally committed as revision 19580 to svn://svn.ffmpeg.org/ffmpeg/trunk
Includes mmx2 asm for the various functions.
Note that the actual idct still does not have an x86 SIMD implemtation.
For wmv3 files using regular idct, the decoder just falls back to simple_idct,
since simple_idct_dc doesn't exist (yet).
Originally committed as revision 19204 to svn://svn.ffmpeg.org/ffmpeg/trunk
Fixes compilation on 32-bit llvm which didn't allow a cast in an m operand.
Originally committed as revision 19086 to svn://svn.ffmpeg.org/ffmpeg/trunk
Reading above src[-2] isn't safe, so move loads and palignr ahead
3 pixels to load starting at the first pixel actually used.
Fixes issue941.
Originally committed as revision 18999 to svn://svn.ffmpeg.org/ffmpeg/trunk
12.59% overall speedup in x86_32
9.98% overall speedup in x86_64
compared to gcc 4.3.3
Originally committed as revision 18903 to svn://svn.ffmpeg.org/ffmpeg/trunk
pixels, not (dst+pix)>>1.
This makes the mmx functions bitexact with the C functions.
Originally committed as revision 18527 to svn://svn.ffmpeg.org/ffmpeg/trunk
