On Thu, Oct 08, 2015 at 08:22:51AM +0200, Christophe Gisquet wrote: > On 12 frames of a 444p 12 bits DNxHR sequence: > C: 78902 decicycles in idct, 262071 runs, 73 skips > avx: 32478 decicycles in idct, 262045 runs, 99 skips > > Difference between the 2: > stddev: 0.39 PSNR:104.47 MAXDIFF: 2 > > This is unavoidable and due to the scale factors used in the x86 > version, which cannot match the C ones, as this would cause > overflows (there's one less 1bit of precision). > --- > libavcodec/x86/idctdsp_init.c | 19 +++++++++++++++++-- > libavcodec/x86/simple_idct.h | 3 +++ > libavcodec/x86/simple_idct10.asm | 18 +++++++++++++++--- > 3 files changed, 35 insertions(+), 5 deletions(-)
this causes overflows somewhere with mjpeg see https://trac.ffmpeg.org/attachment/ticket/4683/12bpp.jpg [...] -- Michael GnuPG fingerprint: 9FF2128B147EF6730BADF133611EC787040B0FAB I know you won't believe me, but the highest form of Human Excellence is to question oneself and others. -- Socrates
signature.asc
Description: Digital signature
_______________________________________________ ffmpeg-devel mailing list ffmpeg-devel@ffmpeg.org http://ffmpeg.org/mailman/listinfo/ffmpeg-devel
