On Sat, Aug 11, 2018 at 05:52:32PM +0300, Sergey Lavrushkin wrote: > 2018-08-10 20:24 GMT+03:00 Michael Niedermayer <mich...@niedermayer.cc>: > > > On Thu, Aug 09, 2018 at 08:15:16PM +0300, Sergey Lavrushkin wrote: > > > Here are updated patches with fixes. I updated conversion functions, so > > > they should > > > properly work with format for different endianness. > > [...] > > > diff --git a/libswscale/input.c b/libswscale/input.c > > > index 3fd3a5d81e..0e016d387f 100644 > > > --- a/libswscale/input.c > > > +++ b/libswscale/input.c > > > @@ -942,6 +942,30 @@ static av_always_inline void > > planar_rgb16_to_uv(uint8_t *_dstU, uint8_t *_dstV, > > > } > > > #undef rdpx > > > > > > +static av_always_inline void grayf32ToY16_c(uint8_t *_dst, const > > uint8_t *_src, const uint8_t *unused1, > > > + const uint8_t *unused2, int > > width, uint32_t *unused) > > > +{ > > > + int i; > > > + const float *src = (const float *)_src; > > > + uint16_t *dst = (uint16_t *)_dst; > > > + > > > + for (i = 0; i < width; ++i){ > > > + dst[i] = lrintf(65535.0f * FFMIN(FFMAX(src[i], 0.0f), 1.0f)); > > > + } > > > +} > > > > is it faster to clip the float before lrintf() than the integer afterwards > > ? > > > > Clipping integers is faster, switched to it. > > > > [...] > > > diff --git a/libswscale/output.c b/libswscale/output.c > > > index 0af2fffea4..cd408fb285 100644 > > > --- a/libswscale/output.c > > > +++ b/libswscale/output.c > > > @@ -208,6 +208,121 @@ static void yuv2p016cX_c(SwsContext *c, const > > int16_t *chrFilter, int chrFilterS > > > } > > > } > > > > > > +static av_always_inline void > > > +yuv2plane1_float_c_template(const int32_t *src, float *dest, int dstW) > > > +{ > > > +#if HAVE_BIGENDIAN > > > + static const int big_endian = 1; > > > +#else > > > + static const int big_endian = 0; > > > +#endif > > > > you can use HAVE_BIGENDIAN in place of big_endian > > its either 0 or 1 already > > or static const int big_endian = HAVE_BIGENDIAN > > > > Ok. > > Here is updated patch.
> libswscale/input.c | 38 +++++++++++ > libswscale/output.c | 105 > +++++++++++++++++++++++++++++++ > libswscale/ppc/swscale_altivec.c | 1 > libswscale/swscale_internal.h | 9 ++ > libswscale/swscale_unscaled.c | 54 +++++++++++++++ > libswscale/utils.c | 20 +++++ > libswscale/x86/swscale_template.c | 3 > tests/ref/fate/filter-pixdesc-grayf32be | 1 > tests/ref/fate/filter-pixdesc-grayf32le | 1 > tests/ref/fate/filter-pixfmts-copy | 2 > tests/ref/fate/filter-pixfmts-crop | 2 > tests/ref/fate/filter-pixfmts-field | 2 > tests/ref/fate/filter-pixfmts-fieldorder | 2 > tests/ref/fate/filter-pixfmts-hflip | 2 > tests/ref/fate/filter-pixfmts-il | 2 > tests/ref/fate/filter-pixfmts-null | 2 > tests/ref/fate/filter-pixfmts-scale | 2 > tests/ref/fate/filter-pixfmts-transpose | 2 > tests/ref/fate/filter-pixfmts-vflip | 2 > 19 files changed, 248 insertions(+), 4 deletions(-) > db401051d0e42132f7ce76cb78de584951be704b > 0005-libswscale-Adds-conversions-from-to-float-gray-forma.patch > From cf523bcb50537abbf6daf0eb799341d8b706d366 Mon Sep 17 00:00:00 2001 > From: Sergey Lavrushkin <dual...@gmail.com> > Date: Fri, 3 Aug 2018 18:06:50 +0300 > Subject: [PATCH 5/9] libswscale: Adds conversions from/to float gray format. > > --- > libswscale/input.c | 38 +++++++++++ > libswscale/output.c | 105 > +++++++++++++++++++++++++++++++ > libswscale/ppc/swscale_altivec.c | 1 + > libswscale/swscale_internal.h | 9 +++ > libswscale/swscale_unscaled.c | 54 +++++++++++++++- > libswscale/utils.c | 20 +++++- > libswscale/x86/swscale_template.c | 3 +- > tests/ref/fate/filter-pixdesc-grayf32be | 1 + > tests/ref/fate/filter-pixdesc-grayf32le | 1 + > tests/ref/fate/filter-pixfmts-copy | 2 + > tests/ref/fate/filter-pixfmts-crop | 2 + > tests/ref/fate/filter-pixfmts-field | 2 + > tests/ref/fate/filter-pixfmts-fieldorder | 2 + > tests/ref/fate/filter-pixfmts-hflip | 2 + > tests/ref/fate/filter-pixfmts-il | 2 + > tests/ref/fate/filter-pixfmts-null | 2 + > tests/ref/fate/filter-pixfmts-scale | 2 + > tests/ref/fate/filter-pixfmts-transpose | 2 + > tests/ref/fate/filter-pixfmts-vflip | 2 + > 19 files changed, 248 insertions(+), 4 deletions(-) > create mode 100644 tests/ref/fate/filter-pixdesc-grayf32be > create mode 100644 tests/ref/fate/filter-pixdesc-grayf32le > > diff --git a/libswscale/input.c b/libswscale/input.c > index 3fd3a5d81e..7e45df50ce 100644 > --- a/libswscale/input.c > +++ b/libswscale/input.c > @@ -942,6 +942,30 @@ static av_always_inline void planar_rgb16_to_uv(uint8_t > *_dstU, uint8_t *_dstV, > } > #undef rdpx > > +static av_always_inline void grayf32ToY16_c(uint8_t *_dst, const uint8_t > *_src, const uint8_t *unused1, > + const uint8_t *unused2, int > width, uint32_t *unused) > +{ > + int i; > + const float *src = (const float *)_src; > + uint16_t *dst = (uint16_t *)_dst; > + > + for (i = 0; i < width; ++i){ > + dst[i] = FFMIN(FFMAX(lrintf(65535.0f * src[i]), 0), 65535); this should use a intermediate variable as FFMIN/MAX are macros so the compiler would have to recognize and eliminate alot of duplicate expressions if the arguments to FFMIN/MAX are complicated thx [...] -- Michael GnuPG fingerprint: 9FF2128B147EF6730BADF133611EC787040B0FAB Into a blind darkness they enter who follow after the Ignorance, they as if into a greater darkness enter who devote themselves to the Knowledge alone. -- Isha Upanishad
signature.asc
Description: PGP signature
_______________________________________________ ffmpeg-devel mailing list ffmpeg-devel@ffmpeg.org http://ffmpeg.org/mailman/listinfo/ffmpeg-devel