After a lot of work by all involved this is the latest patch set. This includes
the results of Ronald's work: rounding, minor coeff differences, "DC only hack".
I need a proper term for this "DC only hack" because it is not DC only. It is
for the lowest frequency of each row.
I squashed all 3 functions together because it is not correct to use only some
of them due to the differences in permutation required by these and the C/MMX
functions.
I would appreciate it if people could run the new fate test
(fate-idct-simpleauto) on ARM neon and armv5te. No other platforms use their
own functions for simpleauto.
I might follow this with a patch to cleanup idctdsp_init.c
James Darnley (6):
fate: add test of -idct simpleauto
avcodec/x86: cleanup simple_idct10
avcodec/x86: modify simple_idct10 macros to add an action paramter
avcodec/x86: allow future 8-bit simple idct to use slightly different
coefficients
avcodec/x86: allow future 8-bit simple idct to have "DC only hack"
avcodec/x86: add an 8-bit simple IDCT function based on the x86-64
high depth functions
libavcodec/tests/x86/dct.c | 2 +
libavcodec/x86/idctdsp_init.c | 23 ++++
libavcodec/x86/proresdsp.asm | 22 ++--
libavcodec/x86/simple_idct.h | 9 ++
libavcodec/x86/simple_idct10.asm | 139 +++++++++++++++++++++---
libavcodec/x86/simple_idct10_template.asm | 174 +++++++++++++++++++-----------
tests/fate/video.mak | 3 +
tests/ref/fate/idct-simpleauto | 27 +++++
8 files changed, 312 insertions(+), 87 deletions(-)
create mode 100644 tests/ref/fate/idct-simpleauto
--
2.13.1
_______________________________________________
ffmpeg-devel mailing list
ffmpeg-devel@ffmpeg.org
http://ffmpeg.org/mailman/listinfo/ffmpeg-devel
