The AArch64 assembly accesses those symbols directly, without
indirection via e.g. the GOT on ELF. In order for this not to
require text relocations, those symbols need to be resolved fully
at link time, i.e. those symbols can't be interposable.
Normally, so far, this is achieved when linking shared libraries
in two ways; we have a version script (libavcodec/libavcodec.v) which
marks all symbols that don't start with av* as local. Additionally,
we try to add -Wl,-Bsymbolic to the linker options if supported,
making sure that such symbol references are resolved fully at link
time, instead of making them interposable.
When the libavcodec static library is linked into another shared
library, there's no guarantee that it uses similar options (even though
that would be favourable), which would end up requiring text relocations
in the AArch64 assembly.
Explicitly mark the symbols that are accessed from AArch64 assembly
as hidden, so that they are resolved fully at link time even without
the version script and -Wl,-Bsymbolic.
Signed-off-by: Martin Storsjö <martin@martin.st>
The sbr_qmf_window_us array is basically symmetric around its middle
element and therefore the latter half is currently initialized from the
first half at runtime. Yet because the first half is initialized, the
array can't be placed in .bss at all, so that one gains nothing from not
already initializing the whole array statically. Therefore this commit
does exactly this.
(There are two exceptions to the symmetry: Elements 384 and 512 are the
negations of their mirror element; for the fixed-point decoder, Q31(-x)
does not equal -Q31(x). In order to keep the array exactly the same, the
latter form has been used for these two elements.)
Reviewed-by: Lynne <dev@lynne.ee>
Signed-off-by: Andreas Rheinhardt <andreas.rheinhardt@gmail.com>
These tables are always initialized at runtime since commit
cb93df0dcb.
Reviewed-by: Lynne <dev@lynne.ee>
Signed-off-by: Andreas Rheinhardt <andreas.rheinhardt@gmail.com>
Create tables for fixed point code.
Signed-off-by: Nedeljko Babic <nedeljko.babic@imgtec.com>
Signed-off-by: Michael Niedermayer <michael@niedermayer.cc>
For sbr_qmf_window_us there is even a question if it maybe
should be fully hardcoded all the time.
Since half of it is coded, it ends up in .data and not .bss.
Signed-off-by: Reimar Döffinger <Reimar.Doeffinger@gmx.de>
233 to 105 cycles on Arrandale and Win64.
Replacing the multiplication by s_m[m] by a pand and a pxor with
appropriate vectors is slower. Unrolling is a 15 cycles win.
A SSE version was 4 cycles slower.
Signed-off-by: Michael Niedermayer <michaelni@gmx.at>
This prepares for assembly optimisations by moving the most
time-consuming loops to functions called through pointers
in a new context.
Signed-off-by: Mans Rullgard <mans@mansr.com>
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
A large portion of this code was orignally authored by Robert Swain. The rest
was written by me. Full history is available at:
svn://svn.ffmpeg.org/soc/aac-sbr
http://github.com/aconverse/ffmpeg-heaac/tree/sbr_pub
Originally committed as revision 22316 to svn://svn.ffmpeg.org/ffmpeg/trunk
Martin Storsjö
Anton Khirnov
Andreas Rheinhardt
James Almer
Jovan Zelincevic
Reimar Döffinger
Christophe Gisquet
Kieran Kunhya
Mans Rullgard
Diego Biurrun
Alex Converse