Commit Graph

15 Commits

Author SHA1 Message Date
Clément Bœsch e8bc642202 lavu: add AV_CEIL_RSHIFT and use it in various places
Signed-off-by: Vittorio Giovara <vittorio.giovara@gmail.com>
2016-01-11 15:32:56 -05:00
Diego Biurrun aba70bb538 Add missing headers to make template files compile (more) standalone 2014-03-26 04:31:27 -07:00
Michael Niedermayer 91c981857b rgb2rgb_template: add MMX/SSE2/AVX-optimized deinterleaveBytes
Signed-off-by: Anton Khirnov <anton@khirnov.net>
2014-01-21 18:03:41 +01:00
Michael Niedermayer 7597e6efe4 swscale/x86/rgb2rgb: add support for AVX
This does not yet include any actual AVX code

Signed-off-by: Anton Khirnov <anton@khirnov.net>
2014-01-21 18:01:29 +01:00
Diego Biurrun 2b677ffca5 swscale: Add av_cold attributes to init functions missing them 2013-05-04 22:48:05 +02:00
Diego Biurrun 652f518594 x86: mmx2 ---> mmxext in comments and messages 2012-10-31 00:37:42 +01:00
Giorgio Vazzana 1e6072139b swscale: x86: fix #endif comments in rgb2rgb template file
Signed-off-by: Diego Biurrun <diego@biurrun.de>
2012-08-19 21:50:09 +02:00
Mans Rullgard 90540c2d5a x86: swscale: fix fragile memory accesses
To access data at multiple fixed offsets from a base address, this
code uses a single "m" operand and code of the form "32%0", relying on
the memory operand instantiation having no displacement, giving a final
result of the form "32(%rax)".  If the compiler uses a register and
displacement, e.g. "64(%rax)", the end result becomes "3264(%rax)",
which obviously does not work.

Replacing the "m" operands with "r" operands allows safe addition of a
displacement.  In theory, multiple memory operands could use a shared
base register with different index registers, "(%rax,%rbx)", potentially
making more efficient use of registers.  In the cases at hand, no such
sharing is possible since the addresses involved are entirely unrelated.

After this change, the code somewhat rudely accesses memory without
using a corresponding memory operand, which in some cases can lead to
unwanted "optimisations" of surrounding code.  However, the original
code also accesses memory not covered by a memory operand, so this is
not adding any defect not already present.  It is also hightly unlikely
that any such optimisations could be performed here since the memory
locations in questions are not accessed elsewhere in the same functions.

This fixes crashes with suncc.

Signed-off-by: Mans Rullgard <mans@mansr.com>
2012-08-13 14:51:52 +01:00
Mans Rullgard 10b83cb653 x86: swscale: remove disabled code
This code has been disabled since 2003.  Nobody will ever look at
it again.

Signed-off-by: Mans Rullgard <mans@mansr.com>
2012-08-13 14:51:52 +01:00
Diego Biurrun 239fdf1b4a x86: build: replace mmx2 by mmxext
Refactoring mmx2/mmxext YASM code with cpuflags will force renames.
So switching to a consistent naming scheme beforehand is sensible.
The name "mmxext" is more official and widespread and also the name
of the CPU flag, as reported e.g. by the Linux kernel.
2012-08-03 22:51:05 +02:00
Anton Khirnov b8e893399f sws: replace all long with int.
Signed-off-by: Ronald S. Bultje <rsbultje@gmail.com>
2011-05-28 10:03:37 -04:00
Ronald S. Bultje 522d65ba25 rgb2rgb: remove duplicate mmx/mmx2/3dnow/sse2 functions.
Many functions have such a prefix, but do not actually use any
instructions or features from that set, thus giving the false
impression that swscale is highly optimized for a particular
system, whereas in reality it is not.
2011-05-26 09:31:02 -04:00
Michael Niedermayer 7dc303a60e swscale: Eliminate rgb24toyv12_c() duplication.
Signed-off-by: Michael Niedermayer <michaelni@gmx.at>
Signed-off-by: Diego Biurrun <diego@biurrun.de>
2011-05-26 00:56:06 +02:00
Luca Barbato 6216fc70b7 swscale: simplify rgb2rgb templating
MMX is always built. Drop the ifdefs
2011-04-14 22:16:47 +02:00
Luca Barbato c003832883 swscale: move away x86 specific code from rgb2rgb
Keep only the plain C code in the main rgb2rgb.c and move the x86
specific optimizations to x86/rgb2rgb.c
Change the initialization pattern a little so some of it can be
factorized to behave more like dsputils.
2011-04-14 22:16:47 +02:00