This is ~2x faster for y not an integer on Haswell+GCC, and should
generally be faster due to the fact that anyway powf essentially does
this under the hood. Made an inline function in lavu/internal.h for this
purpose.
Note that there are some accuracy differences, that should generally be
negligible. In particular, FATE still passes on this platform.
Results in ~ 7% speedup in aac encoding with -march=native, Haswell+GCC.
before:
ffmpeg -i sin.flac -acodec aac -y sin_new.aac 6.05s user 0.06s system 104% cpu 5.821 total
after:
ffmpeg -i sin.flac -acodec aac -y sin_new.aac 5.67s user 0.03s system 105% cpu 5.416 total
This is also faster than an alternative approach that pulls in powf, gets rid of
the crufty NaN checks and other special cases, exploits knowledge about the intervals, etc.
This of course does not exclude smarter approaches; just suggests that
there would need to be significant work on this front of lower utility than
searches for hotspots elsewhere.
Reviewed-by: Reimar Döffinger <Reimar.Doeffinger@gmx.de>
Reviewed-by: Ronald S. Bultje <rsbultje@gmail.com>
Signed-off-by: Ganesh Ajjanagadde <gajjanag@gmail.com>
(cherry picked from commit bccc81dfa08e6561df6ed37860e3a08f7d983825)
This should theoretically improve the randomness slightly
Signed-off-by: Michael Niedermayer <michael@niedermayer.cc>
(cherry picked from commit 2540d884f3fd7cfac503e048112098967be2569a)
Signed-off-by: Michael Niedermayer <michael@niedermayer.cc>
Trying to make heads and tails out of DTS 6.1 I can across this typo.
I also noticed that this wiki page is incorrect or misleading, the
channel order for 6.1 given does not match the source code. At the
least it should be clarified that the layout given does not apply to
DTS. https://trac.ffmpeg.org/wiki/AudioChannelManipulation
Signed-off-by: Michael Niedermayer <michael@niedermayer.cc>
(cherry picked from commit 73d1398f0c4ce2de16790f46e05a79242137d153)
Signed-off-by: Michael Niedermayer <michael@niedermayer.cc>
Signed-off-by: Michael Niedermayer <michael@niedermayer.cc>
(cherry picked from commit 1ec7a703806049265991723a8826bd61555edef4)
Signed-off-by: Michael Niedermayer <michael@niedermayer.cc>
Reviewed-by: Michael Niedermayer <michael@niedermayer.cc>
Signed-off-by: James Almer <jamrial@gmail.com>
(cherry picked from commit 70d685a77f283b110e7b1ab565ff5de53f752d55)
Reviewed-by: Michael Niedermayer <michael@niedermayer.cc>
Signed-off-by: James Almer <jamrial@gmail.com>
(cherry picked from commit 73a4589d4b0d97cbd6f8bf8be18b78151b657898)
This was suggested by wm4 and stefano.
After this patch using align=1 the size used by various functions would not
contain padding, while the palette would be aligned at align>1
This patch makes it required to use align>=4 if the palette is to be accessed
as uint32
As a side-effect It fixes storing pal8 in nut with odd with&height
Signed-off-by: Michael Niedermayer <michael@niedermayer.cc>
This allows disabling the alignment by using a compact buffer
Reviewed-by: Stefano Sabatini <stefasab@gmail.com>
Signed-off-by: Michael Niedermayer <michael@niedermayer.cc>
This will extend the whitelist features to allow blacklisting individual protocols and to
explicitly force everything to be enabled.
Reviewed-by: Stefano Sabatini <stefasab@gmail.com>
Signed-off-by: Michael Niedermayer <michael@niedermayer.cc>
(this structure is not referenced anywhere yet)
Signed-off-by: Neil Birkbeck <neil.birkbeck@gmail.com>
Signed-off-by: Michael Niedermayer <michael@niedermayer.cc>
Libav, for some reason, merged this as a public API function. This will
aid in future merges.
A define is left for backwards compat, just in case some person
used it, since it is in a public header.
Signed-off-by: Derek Buitenhuis <derek.buitenhuis@gmail.com>
Add names for recently added enums to av_frame_side_data_name.
Signed-off-by: Neil Birkbeck <neil.birkbeck@gmail.com>
Signed-off-by: Michael Niedermayer <michael@niedermayer.cc>
Some debuggers/profilers use this metadata to determine which function a
given instruction is in; without it they get can confused by local labels
(if you haven't stripped those). On the other hand, some tools are still
confused even with this metadata. e.g. this fixes `gdb`, but not `perf`.
Currently only implemented for ELF.
The REP_RET workaround is only needed on old AMD cpus, and the labels clutter
up the symbol table and confuse debugging/profiling tools, so use EQU to
create SHN_ABS symbols instead of creating local labels. Furthermore, skip
the workaround completely in functions that definitely won't run on such cpus.
Note that EQU is just creating a local label when using nasm instead of yasm.
This is probably a bug, but at least it doesn't break anything.
When allocating stack space with a larger alignment than the known stack
alignment a temporary register is used for storing the stack pointer.
Ensure that this isn't one of the registers used for passing arguments.
* Correctly handle FMA instructions with memory operands.
* Print a warning if FMA instructions are used without the correct cpuflag.
* Simplify the instantiation code.
* Clarify documentation.
Only the last operand in FMA3 instructions can be a memory operand. When
converting FMA4 instructions to FMA3 instructions we can utilize the fact
that multiply is a commutative operation and reorder operands if necessary
to ensure that a memory operand is used only as the last operand.
It seems to miscompile them
Should fix fate-ra-288 and fate-twinvq
Reviewed-by: Michael Niedermayer <michael@niedermayer.cc>
Signed-off-by: James Almer <jamrial@gmail.com>
Adding mastering display metadata struct to avutil. The mastering display metadata contains information
about the mastering display color volume (SMPTE 2086:2014).
This info comes from HEVC in the SEI_TYPE_MASTERING_DISPLAY_INFO and is soon to be included in MKV:
https://mailarchive.ietf.org/arch/search/?email_list=cellar&gbt=1&index=sZyfPTM-QY69P-0omfOIiTN622o
so it is similar to SEI FPA / stereo_mode in MKV and as such this patch follows how AVStereo3D is implemented.
I'll add support to HEVC in a follow-up (and MKV when spec is approved).
Signed-off-by: Neil Birkbeck <neil.birkbeck@gmail.com>
Signed-off-by: Michael Niedermayer <michael@niedermayer.cc>
* commit '73c8c0341cce9e1a6c4169721f5123f97fc4be2f':
arm: Fix vfp dead code elimination with have_vfp_vm
Merged-by: Hendrik Leppkes <h.leppkes@gmail.com>
This fixes ubsan runtime error: signed integer overflow: 8388608 +
2140274688 cannot be represented in type 'int'
Reviewed-by: Michael Niedermayer <michael@niedermayer.cc>
Signed-off-by: Andreas Cadhalpun <Andreas.Cadhalpun@googlemail.com>
This fixes builds with --disable-vfp.
Checking for the armv6 cpu flag is incorrect, since vfpv2 isn't
armv6 specific.
Signed-off-by: Martin Storsjö <martin@martin.st>
