Commit Graph

34 Commits

Author SHA1 Message Date
Mans Rullgard 5b0d35eaed x86: bswap: remove test for bswap instruction
Firstly, this test never worked as intended, always reporting
success.  Secondly, bswap is available from 486 onward and can
thus be assumed present.

Signed-off-by: Mans Rullgard <mans@mansr.com>
2011-12-12 12:14:15 +00:00
Mans Rullgard f64c2e710f bswap: make generic implementation more compiler-friendly
With these changes, gcc 4.5 and later recognise it as a bswap
and use the proper instructions on ARM and x86.  On x86, the
16-bit bswap is recognised from gcc 4.1.

Signed-off-by: Mans Rullgard <mans@mansr.com>
2011-12-12 12:14:14 +00:00
Sean McGovern be0675ce67 x86 cpuid: set vendor union members separately
Solaris Studio (suncc) has difficulty with filling in
members of a union. Instead, let's retrieve and store the
cpuid() results separately. This is still a compiler bug,
however this fix does not cause a regression on other platforms.

Signed-off-by: Janne Grunau <janne-libav@jannau.net>
2011-12-08 00:57:11 +01:00
Vitor Sessak 6b6ee58249 x86inc: Flag shufps as an floating-point instruction for the AVX emulation code.
Without this, code like "shufps m0, m1, m2, 0xaa" would not work in CPUs
not supporting SSE2.

Signed-off-by: Ronald S. Bultje <rsbultje@gmail.com>
2011-11-27 13:10:33 -08:00
Justin Ruggles f2bd8a0786 x86inc: use sse versions of common macros instead of sse2 when applicable 2011-11-06 19:14:13 -05:00
Loren Merritt 2f7f2e4b41 Update x86inc.asm to latest x264 version, and add AVX symmetry.
We keep INIT_AVX (for backwards compatibility). 3arg AVX ops with
a memory arg can only have it in src2, whereas SSE emulation of
3arg prefers to have it in src1 (i.e. the mov). So, if the op is
symmetric and the wrong one is memory, swap them.
2011-11-05 20:48:14 -07:00
Justin Ruggles 4e8e262476 fmtconvert: port int32_to_float_fmul_scalar() x86 inline asm to yasm 2011-10-21 10:13:05 -04:00
Jason Garrett-Glaser 96a59cf37b x86: XOP/FMA4 CPU detection support 2011-09-26 15:30:31 -07:00
Sean McGovern 5938e02185 cpu detection: avoid a signed overflow
1<<31 overflows because 1 is signed, so force it to unsigned.

Signed-off-by: Ronald S. Bultje <rsbultje@gmail.com>
2011-09-03 08:31:50 -07:00
Ronald S. Bultje 38e06c2969 Move clipd macros to x86util.asm.
This allows sharing them between multiple .asm files.
2011-08-17 20:56:06 -07:00
Ronald S. Bultje b2c087871d Move x86util.asm from libavcodec/ to libavutil/.
This allows using it in swscale also.
2011-08-12 11:43:03 -07:00
Ronald S. Bultje 3a39195b1d Move x86inc.asm to libavutil/.
This allows using it in libswscale/ also.
2011-08-12 11:43:02 -07:00
Jason Garrett-Glaser 15919ee48f bswap: use native types for av_bwap16().
This prevents a call to bytestream_get_be16() using a movzwl both before
and after the ror instruction, which is obviously inefficient. Arm uses
the same trick also.

Sintel decoding goes from (avg+SD) 9.856 +/- 0.003 to 9.797 +/- 0.003 sec.

Signed-off-by: Ronald S. Bultje <rsbultje@gmail.com>
2011-04-22 20:05:48 -04:00
Justin Ruggles 45ed822550 cosmetics: indentation 2011-03-22 09:11:07 -04:00
Justin Ruggles eba586b0d9 Add a CPU flag for the Atom processor.
The Atom has SSSE3 support, which is useful in many cases, but sometimes the
SSSE3 version is slower than the SSE2 equivalent on the Atom, but is generally
faster on other processors supporting SSSE3. This flag allows for selectively
disabling certain SSSE3 functions on the Atom.
2011-03-22 09:11:07 -04:00
Mans Rullgard 2912e87a6c Replace FFmpeg with Libav in licence headers
Signed-off-by: Mans Rullgard <mans@mansr.com>
2011-03-19 13:33:20 +00:00
Mans Rullgard ef66953875 x86: use raw opcode for xgetbv instruction
This allows the CPU detection to work with assemblers not supporting
the xgetbv mnemonic.  These include clang and some BSD versions.

All AVX code will be written for yasm, where the main assembler
is not involved.

Signed-off-by: Mans Rullgard <mans@mansr.com>
2011-02-20 17:31:23 +00:00
Mans Rullgard 87f1355f9b x86: check for AVX support
This adds configure and runtime checks for AVX support on x86 CPUs.

Signed-off-by: Mans Rullgard <mans@mansr.com>
2011-02-20 13:20:42 +00:00
Justin Ruggles 74b1f96859 Add check for Athlon64 and similar AMD processors with slow SSE2.
Signed-off-by: Ronald S. Bultje <rsbultje@gmail.com>
2011-02-11 16:58:18 -05:00
Janne Grunau 2c3589bfda consolidate .gitignore patters into a single file
Signed-off-by: Janne Grunau <janne-ffmpeg@jannau.net>
2011-01-18 21:32:05 +01:00
Janne Grunau 348b8218f7 convert svn:ignore properties to .gitignore files
Signed-off-by: Janne Grunau <janne-ffmpeg@jannau.net>
2011-01-17 15:50:14 +01:00
Måns Rullgård 65d45cea34 Add missing #include <string.h> in x86/cpu.c
Originally committed as revision 25088 to svn://svn.ffmpeg.org/ffmpeg/trunk
2010-09-09 19:40:59 +00:00
Måns Rullgård 9275438a19 Clean up av_get_cpu_flag()
Instead of defining functions in per-arch header files included
by the main cpu.c, define them normally and call them from the
generic one.

Originally committed as revision 25084 to svn://svn.ffmpeg.org/ffmpeg/trunk
2010-09-09 18:51:45 +00:00
Stefano Sabatini c6c98d0897 Move mm_support() from libavcodec to libavutil, make it a public
function and rename it to av_get_cpu_flags().

Originally committed as revision 25076 to svn://svn.ffmpeg.org/ffmpeg/trunk
2010-09-08 15:07:14 +00:00
Måns Rullgård 8fc0162ac4 Add av_ prefix to bswap macros
Originally committed as revision 24170 to svn://svn.ffmpeg.org/ffmpeg/trunk
2010-07-10 22:12:30 +00:00
Diego Biurrun ba87f0801d Remove explicit filename from Doxygen @file commands.
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
2010-04-20 14:45:34 +00:00
Måns Rullgård 2ed6f39944 Replace many includes of libavutil/common.h with what is actually needed
This reduces the number of false dependencies on header files and
speeds up compilation.

Originally committed as revision 22407 to svn://svn.ffmpeg.org/ffmpeg/trunk
2010-03-09 17:39:19 +00:00
Måns Rullgård 9c9a0840d0 Add lots of missing includes
Originally committed as revision 22337 to svn://svn.ffmpeg.org/ffmpeg/trunk
2010-03-08 18:43:52 +00:00
Måns Rullgård 75fb5c24ed Move FASTDIV macro to intmath.h
Originally committed as revision 21335 to svn://svn.ffmpeg.org/ffmpeg/trunk
2010-01-19 23:25:36 +00:00
Alexander Strange f6d0390657 Add macros for 64- and 128-bit write-combining optimization to intreadwrite.h.
Add x86 implementation using MMX/SSE.

Originally committed as revision 21281 to svn://svn.ffmpeg.org/ffmpeg/trunk
2010-01-18 10:24:33 +00:00
Måns Rullgård 439ccc4e0e Split libavutil/timer.h per architecture
Originally committed as revision 18304 to svn://svn.ffmpeg.org/ffmpeg/trunk
2009-04-01 22:56:22 +00:00
Diego Biurrun bad5537e2c Use full internal pathname in doxygen @file directives.
Otherwise doxygen complains about ambiguous filenames when files exist
under the same name in different subdirectories.

Originally committed as revision 16912 to svn://svn.ffmpeg.org/ffmpeg/trunk
2009-02-01 02:00:19 +00:00
Aurelien Jacobs b250f9c66d Change semantic of CONFIG_*, HAVE_* and ARCH_*.
They are now always defined to either 0 or 1.

Originally committed as revision 16590 to svn://svn.ffmpeg.org/ffmpeg/trunk
2009-01-13 23:44:16 +00:00
Måns Rullgård 3a90480ac4 split bswap.h into per-arch files
Originally committed as revision 15663 to svn://svn.ffmpeg.org/ffmpeg/trunk
2008-10-21 22:29:57 +00:00