[FFmpeg-devel] [PATCH 10/11] avcodec/x86: add an 8-bit simple IDCT function based on the x86-64 high depth functions

Michael Niedermayer michael at niedermayer.cc
Sat Jun 24 22:27:22 EEST 2017

On Mon, Jun 19, 2017 at 05:11:03PM +0200, James Darnley wrote:
> Includes add/put functions
> Rounding contributed by Ronald S. Bultje
> ---
>  libavcodec/tests/x86/dct.c                |  2 +
>  libavcodec/x86/idctdsp_init.c             | 23 ++++++++
>  libavcodec/x86/simple_idct.h              |  9 +++
>  libavcodec/x86/simple_idct10.asm          | 92 +++++++++++++++++++++++++++++++
>  libavcodec/x86/simple_idct10_template.asm |  6 +-
>  5 files changed, 130 insertions(+), 2 deletions(-)

Sorry for the delay, testing this took me a bit longer than expected
as many files change slightly and looking at differences manually
is manual work ...

This patch changes the default IDCT on x86(64), which is intended IIUC
It also changes the IDCT when simplemmx is set

but on x86-32 simplemmx does after this patch not produce the same
result as simplemmx on x86-64.

iam not sure but
maybe the changed code should enable on FF_IDCT_SIMPLE instead of
whats your oppinion on this ?
the next patch would add FF_IDCT_SIMPLE but it also leaves

Michael     GnuPG fingerprint: 9FF2128B147EF6730BADF133611EC787040B0FAB

What does censorship reveal? It reveals fear. -- Julian Assange
-------------- next part --------------
A non-text attachment was scrubbed...
Name: signature.asc
Type: application/pgp-signature
Size: 181 bytes
Desc: Digital signature
URL: <http://ffmpeg.org/pipermail/ffmpeg-devel/attachments/20170624/c2f63933/attachment.sig>

More information about the ffmpeg-devel mailing list