| Message ID | 20241008225027.12209-6-jamrial@gmail.com |
|---|---|
| State | New |
| Headers | show |
| Series | None | expand |
On Tue, Oct 08, 2024 at 07:50:11PM -0300, James Almer wrote: > Signed-off-by: James Almer <jamrial@gmail.com> > --- > libswscale/output.c | 323 ++++++++++++----------- > libswscale/utils.c | 2 +- > tests/ref/fate/filter-pixdesc-ayuv | 1 + > tests/ref/fate/filter-pixfmts-copy | 1 + > tests/ref/fate/filter-pixfmts-crop | 1 + > tests/ref/fate/filter-pixfmts-field | 1 + > tests/ref/fate/filter-pixfmts-fieldorder | 1 + > tests/ref/fate/filter-pixfmts-hflip | 1 + > tests/ref/fate/filter-pixfmts-il | 1 + > tests/ref/fate/filter-pixfmts-null | 1 + > tests/ref/fate/filter-pixfmts-pad | 1 + > tests/ref/fate/filter-pixfmts-scale | 1 + > tests/ref/fate/filter-pixfmts-transpose | 1 + > tests/ref/fate/filter-pixfmts-vflip | 1 + > 14 files changed, 183 insertions(+), 154 deletions(-) > create mode 100644 tests/ref/fate/filter-pixdesc-ayuv > > diff --git a/libswscale/output.c b/libswscale/output.c > index c9dfd6f60a..328b108089 100644 > --- a/libswscale/output.c > +++ b/libswscale/output.c > @@ -2668,165 +2668,177 @@ yuv2xv36le_X_c(SwsContext *c, const int16_t *lumFilter, > } > } > > -static void > -yuv2vuyX_1_c(SwsContext *c, const int16_t *buf0, > - const int16_t *ubuf[2], const int16_t *vbuf[2], > - const int16_t *abuf0, uint8_t *dest, int dstW, > - int uvalpha, int y) > -{ > - int hasAlpha = !!abuf0; > - int i; > - > - if (uvalpha < 2048) { > - for (i = 0; i < dstW; i++) { > - int Y = (buf0[i] + 64) >> 7; > - int U = (ubuf[0][i] + 64) >> 7; > - int V = (vbuf[0][i] + 64) >> 7; > - int A = 255; > - > - if (Y & 0x100) > - Y = av_clip_uint8(Y); > - if (U & 0x100) > - U = av_clip_uint8(U); > - if (V & 0x100) > - V = av_clip_uint8(V); > - > - if (hasAlpha) { > - A = (abuf0[i] + 64) >> 7; > - if (A & 0x100) > - A = av_clip_uint8(A); > - } > - > - dest[4 * i ] = V; > - dest[4 * i + 1] = U; > - dest[4 * i + 2] = Y; > - dest[4 * i + 3] = A; > - } > - } else { > - for (i = 0; i < dstW; i++) { > - int Y = (buf0[i] + 64) >> 7; > - int U = (ubuf[0][i] + ubuf[1][i] + 128) >> 8; > - int V = (vbuf[0][i] + vbuf[1][i] + 128) >> 8; > - int A = 255; > - > - if (Y & 0x100) > - Y = av_clip_uint8(Y); > - if (U & 0x100) > - U = av_clip_uint8(U); > - if (V & 0x100) > - V = av_clip_uint8(V); > - > - if (hasAlpha) { > - A = (abuf0[i] + 64) >> 7; > - if (A & 0x100) > - A = av_clip_uint8(A); > - } > - > - dest[4 * i ] = V; > - dest[4 * i + 1] = U; > - dest[4 * i + 2] = Y; > - dest[4 * i + 3] = A; > - } > - } > +#define AYUV_1_WRAPPER(fmt, C0, C1, C2, C3) \ > +static void \ > +yuv2 ## fmt ##_1_c(SwsContext *c, const int16_t *buf0, \ > + const int16_t *ubuf[2], const int16_t *vbuf[2], \ > + const int16_t *abuf0, uint8_t *dest, int dstW, \ > + int uvalpha, int y) \ > +{ \ > + int hasAlpha = !!abuf0; \ > + int i; \ > + \ > + if (uvalpha < 2048) { \ > + for (i = 0; i < dstW; i++) { \ > + int Y = (buf0[i] + 64) >> 7; \ > + int U = (ubuf[0][i] + 64) >> 7; \ > + int V = (vbuf[0][i] + 64) >> 7; \ > + int A = 255; \ > + \ > + if (Y & 0x100) \ > + Y = av_clip_uint8(Y); \ > + if (U & 0x100) \ > + U = av_clip_uint8(U); \ > + if (V & 0x100) \ > + V = av_clip_uint8(V); \ > + \ > + if (hasAlpha) { \ > + A = (abuf0[i] + 64) >> 7; \ > + if (A & 0x100) \ > + A = av_clip_uint8(A); \ > + } \ > + \ > + dest[4 * i ] = (C0); \ > + dest[4 * i + 1] = (C1); \ > + dest[4 * i + 2] = (C2); \ > + dest[4 * i + 3] = (C3); \ > + } \ > + } else { \ > + for (i = 0; i < dstW; i++) { \ > + int Y = (buf0[i] + 64) >> 7; \ > + int U = (ubuf[0][i] + ubuf[1][i] + 128) >> 8; \ > + int V = (vbuf[0][i] + vbuf[1][i] + 128) >> 8; \ > + int A = 255; \ > + \ > + if (Y & 0x100) \ > + Y = av_clip_uint8(Y); \ > + if (U & 0x100) \ > + U = av_clip_uint8(U); \ > + if (V & 0x100) \ > + V = av_clip_uint8(V); \ > + \ > + if (hasAlpha) { \ > + A = (abuf0[i] + 64) >> 7; \ > + if (A & 0x100) \ > + A = av_clip_uint8(A); \ > + } \ > + \ > + dest[4 * i ] = (C0); \ > + dest[4 * i + 1] = (C1); \ > + dest[4 * i + 2] = (C2); \ > + dest[4 * i + 3] = (C3); \ > + } \ > + } \ > } Is there an advantage in using huge multiline macros here ? This is ugly and hard to maintain code. Simply writing a always inline function and trusting that the compiler will inline it should result in more normal C code and the same result (is it faster ? or has some other advanatge ?) thx [...]
On 10/11/2024 7:46 PM, Michael Niedermayer wrote: > On Tue, Oct 08, 2024 at 07:50:11PM -0300, James Almer wrote: >> Signed-off-by: James Almer <jamrial@gmail.com> >> --- >> libswscale/output.c | 323 ++++++++++++----------- >> libswscale/utils.c | 2 +- >> tests/ref/fate/filter-pixdesc-ayuv | 1 + >> tests/ref/fate/filter-pixfmts-copy | 1 + >> tests/ref/fate/filter-pixfmts-crop | 1 + >> tests/ref/fate/filter-pixfmts-field | 1 + >> tests/ref/fate/filter-pixfmts-fieldorder | 1 + >> tests/ref/fate/filter-pixfmts-hflip | 1 + >> tests/ref/fate/filter-pixfmts-il | 1 + >> tests/ref/fate/filter-pixfmts-null | 1 + >> tests/ref/fate/filter-pixfmts-pad | 1 + >> tests/ref/fate/filter-pixfmts-scale | 1 + >> tests/ref/fate/filter-pixfmts-transpose | 1 + >> tests/ref/fate/filter-pixfmts-vflip | 1 + >> 14 files changed, 183 insertions(+), 154 deletions(-) >> create mode 100644 tests/ref/fate/filter-pixdesc-ayuv >> >> diff --git a/libswscale/output.c b/libswscale/output.c >> index c9dfd6f60a..328b108089 100644 >> --- a/libswscale/output.c >> +++ b/libswscale/output.c >> @@ -2668,165 +2668,177 @@ yuv2xv36le_X_c(SwsContext *c, const int16_t *lumFilter, >> } >> } >> >> -static void >> -yuv2vuyX_1_c(SwsContext *c, const int16_t *buf0, >> - const int16_t *ubuf[2], const int16_t *vbuf[2], >> - const int16_t *abuf0, uint8_t *dest, int dstW, >> - int uvalpha, int y) >> -{ >> - int hasAlpha = !!abuf0; >> - int i; >> - >> - if (uvalpha < 2048) { >> - for (i = 0; i < dstW; i++) { >> - int Y = (buf0[i] + 64) >> 7; >> - int U = (ubuf[0][i] + 64) >> 7; >> - int V = (vbuf[0][i] + 64) >> 7; >> - int A = 255; >> - >> - if (Y & 0x100) >> - Y = av_clip_uint8(Y); >> - if (U & 0x100) >> - U = av_clip_uint8(U); >> - if (V & 0x100) >> - V = av_clip_uint8(V); >> - >> - if (hasAlpha) { >> - A = (abuf0[i] + 64) >> 7; >> - if (A & 0x100) >> - A = av_clip_uint8(A); >> - } >> - >> - dest[4 * i ] = V; >> - dest[4 * i + 1] = U; >> - dest[4 * i + 2] = Y; >> - dest[4 * i + 3] = A; >> - } >> - } else { >> - for (i = 0; i < dstW; i++) { >> - int Y = (buf0[i] + 64) >> 7; >> - int U = (ubuf[0][i] + ubuf[1][i] + 128) >> 8; >> - int V = (vbuf[0][i] + vbuf[1][i] + 128) >> 8; >> - int A = 255; >> - >> - if (Y & 0x100) >> - Y = av_clip_uint8(Y); >> - if (U & 0x100) >> - U = av_clip_uint8(U); >> - if (V & 0x100) >> - V = av_clip_uint8(V); >> - >> - if (hasAlpha) { >> - A = (abuf0[i] + 64) >> 7; >> - if (A & 0x100) >> - A = av_clip_uint8(A); >> - } >> - >> - dest[4 * i ] = V; >> - dest[4 * i + 1] = U; >> - dest[4 * i + 2] = Y; >> - dest[4 * i + 3] = A; >> - } >> - } >> +#define AYUV_1_WRAPPER(fmt, C0, C1, C2, C3) \ >> +static void \ >> +yuv2 ## fmt ##_1_c(SwsContext *c, const int16_t *buf0, \ >> + const int16_t *ubuf[2], const int16_t *vbuf[2], \ >> + const int16_t *abuf0, uint8_t *dest, int dstW, \ >> + int uvalpha, int y) \ >> +{ \ >> + int hasAlpha = !!abuf0; \ >> + int i; \ >> + \ >> + if (uvalpha < 2048) { \ >> + for (i = 0; i < dstW; i++) { \ >> + int Y = (buf0[i] + 64) >> 7; \ >> + int U = (ubuf[0][i] + 64) >> 7; \ >> + int V = (vbuf[0][i] + 64) >> 7; \ >> + int A = 255; \ >> + \ >> + if (Y & 0x100) \ >> + Y = av_clip_uint8(Y); \ >> + if (U & 0x100) \ >> + U = av_clip_uint8(U); \ >> + if (V & 0x100) \ >> + V = av_clip_uint8(V); \ >> + \ >> + if (hasAlpha) { \ >> + A = (abuf0[i] + 64) >> 7; \ >> + if (A & 0x100) \ >> + A = av_clip_uint8(A); \ >> + } \ >> + \ >> + dest[4 * i ] = (C0); \ >> + dest[4 * i + 1] = (C1); \ >> + dest[4 * i + 2] = (C2); \ >> + dest[4 * i + 3] = (C3); \ >> + } \ >> + } else { \ >> + for (i = 0; i < dstW; i++) { \ >> + int Y = (buf0[i] + 64) >> 7; \ >> + int U = (ubuf[0][i] + ubuf[1][i] + 128) >> 8; \ >> + int V = (vbuf[0][i] + vbuf[1][i] + 128) >> 8; \ >> + int A = 255; \ >> + \ >> + if (Y & 0x100) \ >> + Y = av_clip_uint8(Y); \ >> + if (U & 0x100) \ >> + U = av_clip_uint8(U); \ >> + if (V & 0x100) \ >> + V = av_clip_uint8(V); \ >> + \ >> + if (hasAlpha) { \ >> + A = (abuf0[i] + 64) >> 7; \ >> + if (A & 0x100) \ >> + A = av_clip_uint8(A); \ >> + } \ >> + \ >> + dest[4 * i ] = (C0); \ >> + dest[4 * i + 1] = (C1); \ >> + dest[4 * i + 2] = (C2); \ >> + dest[4 * i + 3] = (C3); \ >> + } \ >> + } \ >> } > > Is there an advantage in using huge multiline macros here ? > > This is ugly and hard to maintain code. Simply writing a always inline function > and trusting that the compiler will inline it should result in more normal > C code and the same result > > (is it faster ? or has some other advanatge ?) No, just figured doing it like this. I can make it an always inline function.
On Fri, Oct 11, 2024 at 07:54:48PM -0300, James Almer wrote: > On 10/11/2024 7:46 PM, Michael Niedermayer wrote: > > On Tue, Oct 08, 2024 at 07:50:11PM -0300, James Almer wrote: > > > Signed-off-by: James Almer <jamrial@gmail.com> > > > --- > > > libswscale/output.c | 323 ++++++++++++----------- > > > libswscale/utils.c | 2 +- > > > tests/ref/fate/filter-pixdesc-ayuv | 1 + > > > tests/ref/fate/filter-pixfmts-copy | 1 + > > > tests/ref/fate/filter-pixfmts-crop | 1 + > > > tests/ref/fate/filter-pixfmts-field | 1 + > > > tests/ref/fate/filter-pixfmts-fieldorder | 1 + > > > tests/ref/fate/filter-pixfmts-hflip | 1 + > > > tests/ref/fate/filter-pixfmts-il | 1 + > > > tests/ref/fate/filter-pixfmts-null | 1 + > > > tests/ref/fate/filter-pixfmts-pad | 1 + > > > tests/ref/fate/filter-pixfmts-scale | 1 + > > > tests/ref/fate/filter-pixfmts-transpose | 1 + > > > tests/ref/fate/filter-pixfmts-vflip | 1 + > > > 14 files changed, 183 insertions(+), 154 deletions(-) > > > create mode 100644 tests/ref/fate/filter-pixdesc-ayuv > > > > > > diff --git a/libswscale/output.c b/libswscale/output.c > > > index c9dfd6f60a..328b108089 100644 > > > --- a/libswscale/output.c > > > +++ b/libswscale/output.c > > > @@ -2668,165 +2668,177 @@ yuv2xv36le_X_c(SwsContext *c, const int16_t *lumFilter, > > > } > > > } > > > -static void > > > -yuv2vuyX_1_c(SwsContext *c, const int16_t *buf0, > > > - const int16_t *ubuf[2], const int16_t *vbuf[2], > > > - const int16_t *abuf0, uint8_t *dest, int dstW, > > > - int uvalpha, int y) > > > -{ > > > - int hasAlpha = !!abuf0; > > > - int i; > > > - > > > - if (uvalpha < 2048) { > > > - for (i = 0; i < dstW; i++) { > > > - int Y = (buf0[i] + 64) >> 7; > > > - int U = (ubuf[0][i] + 64) >> 7; > > > - int V = (vbuf[0][i] + 64) >> 7; > > > - int A = 255; > > > - > > > - if (Y & 0x100) > > > - Y = av_clip_uint8(Y); > > > - if (U & 0x100) > > > - U = av_clip_uint8(U); > > > - if (V & 0x100) > > > - V = av_clip_uint8(V); > > > - > > > - if (hasAlpha) { > > > - A = (abuf0[i] + 64) >> 7; > > > - if (A & 0x100) > > > - A = av_clip_uint8(A); > > > - } > > > - > > > - dest[4 * i ] = V; > > > - dest[4 * i + 1] = U; > > > - dest[4 * i + 2] = Y; > > > - dest[4 * i + 3] = A; > > > - } > > > - } else { > > > - for (i = 0; i < dstW; i++) { > > > - int Y = (buf0[i] + 64) >> 7; > > > - int U = (ubuf[0][i] + ubuf[1][i] + 128) >> 8; > > > - int V = (vbuf[0][i] + vbuf[1][i] + 128) >> 8; > > > - int A = 255; > > > - > > > - if (Y & 0x100) > > > - Y = av_clip_uint8(Y); > > > - if (U & 0x100) > > > - U = av_clip_uint8(U); > > > - if (V & 0x100) > > > - V = av_clip_uint8(V); > > > - > > > - if (hasAlpha) { > > > - A = (abuf0[i] + 64) >> 7; > > > - if (A & 0x100) > > > - A = av_clip_uint8(A); > > > - } > > > - > > > - dest[4 * i ] = V; > > > - dest[4 * i + 1] = U; > > > - dest[4 * i + 2] = Y; > > > - dest[4 * i + 3] = A; > > > - } > > > - } > > > +#define AYUV_1_WRAPPER(fmt, C0, C1, C2, C3) \ > > > +static void \ > > > +yuv2 ## fmt ##_1_c(SwsContext *c, const int16_t *buf0, \ > > > + const int16_t *ubuf[2], const int16_t *vbuf[2], \ > > > + const int16_t *abuf0, uint8_t *dest, int dstW, \ > > > + int uvalpha, int y) \ > > > +{ \ > > > + int hasAlpha = !!abuf0; \ > > > + int i; \ > > > + \ > > > + if (uvalpha < 2048) { \ > > > + for (i = 0; i < dstW; i++) { \ > > > + int Y = (buf0[i] + 64) >> 7; \ > > > + int U = (ubuf[0][i] + 64) >> 7; \ > > > + int V = (vbuf[0][i] + 64) >> 7; \ > > > + int A = 255; \ > > > + \ > > > + if (Y & 0x100) \ > > > + Y = av_clip_uint8(Y); \ > > > + if (U & 0x100) \ > > > + U = av_clip_uint8(U); \ > > > + if (V & 0x100) \ > > > + V = av_clip_uint8(V); \ > > > + \ > > > + if (hasAlpha) { \ > > > + A = (abuf0[i] + 64) >> 7; \ > > > + if (A & 0x100) \ > > > + A = av_clip_uint8(A); \ > > > + } \ > > > + \ > > > + dest[4 * i ] = (C0); \ > > > + dest[4 * i + 1] = (C1); \ > > > + dest[4 * i + 2] = (C2); \ > > > + dest[4 * i + 3] = (C3); \ > > > + } \ > > > + } else { \ > > > + for (i = 0; i < dstW; i++) { \ > > > + int Y = (buf0[i] + 64) >> 7; \ > > > + int U = (ubuf[0][i] + ubuf[1][i] + 128) >> 8; \ > > > + int V = (vbuf[0][i] + vbuf[1][i] + 128) >> 8; \ > > > + int A = 255; \ > > > + \ > > > + if (Y & 0x100) \ > > > + Y = av_clip_uint8(Y); \ > > > + if (U & 0x100) \ > > > + U = av_clip_uint8(U); \ > > > + if (V & 0x100) \ > > > + V = av_clip_uint8(V); \ > > > + \ > > > + if (hasAlpha) { \ > > > + A = (abuf0[i] + 64) >> 7; \ > > > + if (A & 0x100) \ > > > + A = av_clip_uint8(A); \ > > > + } \ > > > + \ > > > + dest[4 * i ] = (C0); \ > > > + dest[4 * i + 1] = (C1); \ > > > + dest[4 * i + 2] = (C2); \ > > > + dest[4 * i + 3] = (C3); \ > > > + } \ > > > + } \ > > > } > > > > Is there an advantage in using huge multiline macros here ? > > > > This is ugly and hard to maintain code. Simply writing a always inline function > > and trusting that the compiler will inline it should result in more normal > > C code and the same result > > > > (is it faster ? or has some other advanatge ?) > > No, just figured doing it like this. I can make it an always inline > function. please do, we have a few slight differnt ways its done currently, heres one example (and in this example, in fact output_pixels could be itself replaced by a function, which would probably be cleaner too) In fact everything can be cleaned up and i certainly would love to see someone have a brilliant idea to make it cleaner with no disadvanatges ... #define output_pixels(pos, Y1, U, Y2, V) \ if (target == AV_PIX_FMT_YUYV422) { \ dest[pos + 0] = Y1; \ dest[pos + 1] = U; \ dest[pos + 2] = Y2; \ dest[pos + 3] = V; \ } else if (target == AV_PIX_FMT_YVYU422) { \ dest[pos + 0] = Y1; \ dest[pos + 1] = V; \ dest[pos + 2] = Y2; \ dest[pos + 3] = U; \ } else { /* AV_PIX_FMT_UYVY422 */ \ dest[pos + 0] = U; \ dest[pos + 1] = Y1; \ dest[pos + 2] = V; \ dest[pos + 3] = Y2; \ } static av_always_inline void yuv2422_X_c_template(SwsContext *c, const int16_t *lumFilter, const int16_t **lumSrc, int lumFilterSize, const int16_t *chrFilter, const int16_t **chrUSrc, const int16_t **chrVSrc, int chrFilterSize, const int16_t **alpSrc, uint8_t *dest, int dstW, int y, enum AVPixelFormat target) { int i; for (i = 0; i < ((dstW + 1) >> 1); i++) { int j; int Y1 = 1 << 18; int Y2 = 1 << 18; int U = 1 << 18; int V = 1 << 18; for (j = 0; j < lumFilterSize; j++) { Y1 += lumSrc[j][i * 2] * lumFilter[j]; Y2 += lumSrc[j][i * 2 + 1] * lumFilter[j]; } for (j = 0; j < chrFilterSize; j++) { U += chrUSrc[j][i] * chrFilter[j]; V += chrVSrc[j][i] * chrFilter[j]; } Y1 >>= 19; Y2 >>= 19; U >>= 19; V >>= 19; if ((Y1 | Y2 | U | V) & 0x100) { Y1 = av_clip_uint8(Y1); Y2 = av_clip_uint8(Y2); U = av_clip_uint8(U); V = av_clip_uint8(V); } output_pixels(4*i, Y1, U, Y2, V); } } static av_always_inline void yuv2422_2_c_template(SwsContext *c, const int16_t *buf[2], const int16_t *ubuf[2], const int16_t *vbuf[2], const int16_t *abuf[2], uint8_t *dest, int dstW, int yalpha, int uvalpha, int y, enum AVPixelFormat target) { const int16_t *buf0 = buf[0], *buf1 = buf[1], *ubuf0 = ubuf[0], *ubuf1 = ubuf[1], *vbuf0 = vbuf[0], *vbuf1 = vbuf[1]; int yalpha1 = 4096 - yalpha; int uvalpha1 = 4096 - uvalpha; int i; av_assert2(yalpha <= 4096U); av_assert2(uvalpha <= 4096U); for (i = 0; i < ((dstW + 1) >> 1); i++) { int Y1 = (buf0[i * 2] * yalpha1 + buf1[i * 2] * yalpha) >> 19; int Y2 = (buf0[i * 2 + 1] * yalpha1 + buf1[i * 2 + 1] * yalpha) >> 19; int U = (ubuf0[i] * uvalpha1 + ubuf1[i] * uvalpha) >> 19; int V = (vbuf0[i] * uvalpha1 + vbuf1[i] * uvalpha) >> 19; if ((Y1 | Y2 | U | V) & 0x100) { Y1 = av_clip_uint8(Y1); Y2 = av_clip_uint8(Y2); U = av_clip_uint8(U); V = av_clip_uint8(V); } output_pixels(i * 4, Y1, U, Y2, V); } } static av_always_inline void yuv2422_1_c_template(SwsContext *c, const int16_t *buf0, const int16_t *ubuf[2], const int16_t *vbuf[2], const int16_t *abuf0, uint8_t *dest, int dstW, int uvalpha, int y, enum AVPixelFormat target) { const int16_t *ubuf0 = ubuf[0], *vbuf0 = vbuf[0]; int i; if (uvalpha < 2048) { for (i = 0; i < ((dstW + 1) >> 1); i++) { int Y1 = (buf0[i * 2 ]+64) >> 7; int Y2 = (buf0[i * 2 + 1]+64) >> 7; int U = (ubuf0[i] +64) >> 7; int V = (vbuf0[i] +64) >> 7; if ((Y1 | Y2 | U | V) & 0x100) { Y1 = av_clip_uint8(Y1); Y2 = av_clip_uint8(Y2); U = av_clip_uint8(U); V = av_clip_uint8(V); } output_pixels(i * 4, Y1, U, Y2, V); } } else { const int16_t *ubuf1 = ubuf[1], *vbuf1 = vbuf[1]; for (i = 0; i < ((dstW + 1) >> 1); i++) { int Y1 = (buf0[i * 2 ] + 64) >> 7; int Y2 = (buf0[i * 2 + 1] + 64) >> 7; int U = (ubuf0[i] + ubuf1[i]+128) >> 8; int V = (vbuf0[i] + vbuf1[i]+128) >> 8; if ((Y1 | Y2 | U | V) & 0x100) { Y1 = av_clip_uint8(Y1); Y2 = av_clip_uint8(Y2); U = av_clip_uint8(U); V = av_clip_uint8(V); } output_pixels(i * 4, Y1, U, Y2, V); } } } [...]
diff --git a/libswscale/output.c b/libswscale/output.c index c9dfd6f60a..328b108089 100644 --- a/libswscale/output.c +++ b/libswscale/output.c @@ -2668,165 +2668,177 @@ yuv2xv36le_X_c(SwsContext *c, const int16_t *lumFilter, } } -static void -yuv2vuyX_1_c(SwsContext *c, const int16_t *buf0, - const int16_t *ubuf[2], const int16_t *vbuf[2], - const int16_t *abuf0, uint8_t *dest, int dstW, - int uvalpha, int y) -{ - int hasAlpha = !!abuf0; - int i; - - if (uvalpha < 2048) { - for (i = 0; i < dstW; i++) { - int Y = (buf0[i] + 64) >> 7; - int U = (ubuf[0][i] + 64) >> 7; - int V = (vbuf[0][i] + 64) >> 7; - int A = 255; - - if (Y & 0x100) - Y = av_clip_uint8(Y); - if (U & 0x100) - U = av_clip_uint8(U); - if (V & 0x100) - V = av_clip_uint8(V); - - if (hasAlpha) { - A = (abuf0[i] + 64) >> 7; - if (A & 0x100) - A = av_clip_uint8(A); - } - - dest[4 * i ] = V; - dest[4 * i + 1] = U; - dest[4 * i + 2] = Y; - dest[4 * i + 3] = A; - } - } else { - for (i = 0; i < dstW; i++) { - int Y = (buf0[i] + 64) >> 7; - int U = (ubuf[0][i] + ubuf[1][i] + 128) >> 8; - int V = (vbuf[0][i] + vbuf[1][i] + 128) >> 8; - int A = 255; - - if (Y & 0x100) - Y = av_clip_uint8(Y); - if (U & 0x100) - U = av_clip_uint8(U); - if (V & 0x100) - V = av_clip_uint8(V); - - if (hasAlpha) { - A = (abuf0[i] + 64) >> 7; - if (A & 0x100) - A = av_clip_uint8(A); - } - - dest[4 * i ] = V; - dest[4 * i + 1] = U; - dest[4 * i + 2] = Y; - dest[4 * i + 3] = A; - } - } +#define AYUV_1_WRAPPER(fmt, C0, C1, C2, C3) \ +static void \ +yuv2 ## fmt ##_1_c(SwsContext *c, const int16_t *buf0, \ + const int16_t *ubuf[2], const int16_t *vbuf[2], \ + const int16_t *abuf0, uint8_t *dest, int dstW, \ + int uvalpha, int y) \ +{ \ + int hasAlpha = !!abuf0; \ + int i; \ + \ + if (uvalpha < 2048) { \ + for (i = 0; i < dstW; i++) { \ + int Y = (buf0[i] + 64) >> 7; \ + int U = (ubuf[0][i] + 64) >> 7; \ + int V = (vbuf[0][i] + 64) >> 7; \ + int A = 255; \ + \ + if (Y & 0x100) \ + Y = av_clip_uint8(Y); \ + if (U & 0x100) \ + U = av_clip_uint8(U); \ + if (V & 0x100) \ + V = av_clip_uint8(V); \ + \ + if (hasAlpha) { \ + A = (abuf0[i] + 64) >> 7; \ + if (A & 0x100) \ + A = av_clip_uint8(A); \ + } \ + \ + dest[4 * i ] = (C0); \ + dest[4 * i + 1] = (C1); \ + dest[4 * i + 2] = (C2); \ + dest[4 * i + 3] = (C3); \ + } \ + } else { \ + for (i = 0; i < dstW; i++) { \ + int Y = (buf0[i] + 64) >> 7; \ + int U = (ubuf[0][i] + ubuf[1][i] + 128) >> 8; \ + int V = (vbuf[0][i] + vbuf[1][i] + 128) >> 8; \ + int A = 255; \ + \ + if (Y & 0x100) \ + Y = av_clip_uint8(Y); \ + if (U & 0x100) \ + U = av_clip_uint8(U); \ + if (V & 0x100) \ + V = av_clip_uint8(V); \ + \ + if (hasAlpha) { \ + A = (abuf0[i] + 64) >> 7; \ + if (A & 0x100) \ + A = av_clip_uint8(A); \ + } \ + \ + dest[4 * i ] = (C0); \ + dest[4 * i + 1] = (C1); \ + dest[4 * i + 2] = (C2); \ + dest[4 * i + 3] = (C3); \ + } \ + } \ } -static void -yuv2vuyX_2_c(SwsContext *c, const int16_t *buf[2], - const int16_t *ubuf[2], const int16_t *vbuf[2], - const int16_t *abuf[2], uint8_t *dest, int dstW, - int yalpha, int uvalpha, int y) -{ - int hasAlpha = abuf && abuf[0] && abuf[1]; - const int16_t *buf0 = buf[0], *buf1 = buf[1], - *ubuf0 = ubuf[0], *ubuf1 = ubuf[1], - *vbuf0 = vbuf[0], *vbuf1 = vbuf[1], - *abuf0 = hasAlpha ? abuf[0] : NULL, - *abuf1 = hasAlpha ? abuf[1] : NULL; - int yalpha1 = 4096 - yalpha; - int uvalpha1 = 4096 - uvalpha; - int i; - - av_assert2(yalpha <= 4096U); - av_assert2(uvalpha <= 4096U); - - for (i = 0; i < dstW; i++) { - int Y = (buf0[i] * yalpha1 + buf1[i] * yalpha) >> 19; - int U = (ubuf0[i] * uvalpha1 + ubuf1[i] * uvalpha) >> 19; - int V = (vbuf0[i] * uvalpha1 + vbuf1[i] * uvalpha) >> 19; - int A = 255; - - if (Y & 0x100) - Y = av_clip_uint8(Y); - if (U & 0x100) - U = av_clip_uint8(U); - if (V & 0x100) - V = av_clip_uint8(V); - - if (hasAlpha) { - A = (abuf0[i] * yalpha1 + abuf1[i] * yalpha) >> 19; - A = av_clip_uint8(A); - } - - dest[4 * i ] = V; - dest[4 * i + 1] = U; - dest[4 * i + 2] = Y; - dest[4 * i + 3] = A; - } +AYUV_1_WRAPPER(vuyX, V, U, Y, A) +AYUV_1_WRAPPER(ayuv, A, Y, U, V) + +#define AYUV_2_WRAPPER(fmt, C0, C1, C2, C3) \ +static void \ +yuv2 ## fmt ##_2_c(SwsContext *c, const int16_t *buf[2], \ + const int16_t *ubuf[2], const int16_t *vbuf[2], \ + const int16_t *abuf[2], uint8_t *dest, int dstW, \ + int yalpha, int uvalpha, int y) \ +{ \ + int hasAlpha = abuf && abuf[0] && abuf[1]; \ + const int16_t *buf0 = buf[0], *buf1 = buf[1], \ + *ubuf0 = ubuf[0], *ubuf1 = ubuf[1], \ + *vbuf0 = vbuf[0], *vbuf1 = vbuf[1], \ + *abuf0 = hasAlpha ? abuf[0] : NULL, \ + *abuf1 = hasAlpha ? abuf[1] : NULL; \ + int yalpha1 = 4096 - yalpha; \ + int uvalpha1 = 4096 - uvalpha; \ + int i; \ + \ + av_assert2(yalpha <= 4096U); \ + av_assert2(uvalpha <= 4096U); \ + \ + for (i = 0; i < dstW; i++) { \ + int Y = (buf0[i] * yalpha1 + buf1[i] * yalpha) >> 19; \ + int U = (ubuf0[i] * uvalpha1 + ubuf1[i] * uvalpha) >> 19; \ + int V = (vbuf0[i] * uvalpha1 + vbuf1[i] * uvalpha) >> 19; \ + int A = 255; \ + \ + if (Y & 0x100) \ + Y = av_clip_uint8(Y); \ + if (U & 0x100) \ + U = av_clip_uint8(U); \ + if (V & 0x100) \ + V = av_clip_uint8(V); \ + \ + if (hasAlpha) { \ + A = (abuf0[i] * yalpha1 + abuf1[i] * yalpha) >> 19; \ + A = av_clip_uint8(A); \ + } \ + \ + dest[4 * i ] = (C0); \ + dest[4 * i + 1] = (C1); \ + dest[4 * i + 2] = (C2); \ + dest[4 * i + 3] = (C3); \ + } \ } -static void -yuv2vuyX_X_c(SwsContext *c, const int16_t *lumFilter, - const int16_t **lumSrc, int lumFilterSize, - const int16_t *chrFilter, const int16_t **chrUSrc, - const int16_t **chrVSrc, int chrFilterSize, - const int16_t **alpSrc, uint8_t *dest, int dstW, int y) -{ - int i; - - for (i = 0; i < dstW; i++) { - int j; - int Y = 1 << 18, U = 1 << 18; - int V = 1 << 18, A = 255; - - for (j = 0; j < lumFilterSize; j++) - Y += lumSrc[j][i] * lumFilter[j]; - - for (j = 0; j < chrFilterSize; j++) - U += chrUSrc[j][i] * chrFilter[j]; - - for (j = 0; j < chrFilterSize; j++) - V += chrVSrc[j][i] * chrFilter[j]; - - Y >>= 19; - U >>= 19; - V >>= 19; - - if (Y & 0x100) - Y = av_clip_uint8(Y); - if (U & 0x100) - U = av_clip_uint8(U); - if (V & 0x100) - V = av_clip_uint8(V); - - if (alpSrc) { - A = 1 << 18; - - for (j = 0; j < lumFilterSize; j++) - A += alpSrc[j][i] * lumFilter[j]; - - A >>= 19; - - if (A & 0x100) - A = av_clip_uint8(A); - } - - dest[4 * i ] = V; - dest[4 * i + 1] = U; - dest[4 * i + 2] = Y; - dest[4 * i + 3] = A; - } +AYUV_2_WRAPPER(vuyX, V, U, Y, A) +AYUV_2_WRAPPER(ayuv, A, Y, U, V) + +#define AYUV_X_WRAPPER(fmt, C0, C1, C2, C3) \ +static void \ +yuv2 ## fmt ##_X_c(SwsContext *c, const int16_t *lumFilter, \ + const int16_t **lumSrc, int lumFilterSize, \ + const int16_t *chrFilter, const int16_t **chrUSrc, \ + const int16_t **chrVSrc, int chrFilterSize, \ + const int16_t **alpSrc, uint8_t *dest, int dstW, int y) \ +{ \ + int i; \ + \ + for (i = 0; i < dstW; i++) { \ + int j; \ + int Y = 1 << 18, U = 1 << 18; \ + int V = 1 << 18, A = 255; \ + \ + for (j = 0; j < lumFilterSize; j++) \ + Y += lumSrc[j][i] * lumFilter[j]; \ + \ + for (j = 0; j < chrFilterSize; j++) \ + U += chrUSrc[j][i] * chrFilter[j]; \ + \ + for (j = 0; j < chrFilterSize; j++) \ + V += chrVSrc[j][i] * chrFilter[j]; \ + \ + Y >>= 19; \ + U >>= 19; \ + V >>= 19; \ + \ + if (Y & 0x100) \ + Y = av_clip_uint8(Y); \ + if (U & 0x100) \ + U = av_clip_uint8(U); \ + if (V & 0x100) \ + V = av_clip_uint8(V); \ + \ + if (alpSrc) { \ + A = 1 << 18; \ + \ + for (j = 0; j < lumFilterSize; j++) \ + A += alpSrc[j][i] * lumFilter[j]; \ + \ + A >>= 19; \ + \ + if (A & 0x100) \ + A = av_clip_uint8(A); \ + } \ + \ + dest[4 * i ] = (C0); \ + dest[4 * i + 1] = (C1); \ + dest[4 * i + 2] = (C2); \ + dest[4 * i + 3] = (C3); \ + } \ } +AYUV_X_WRAPPER(vuyX, V, U, Y, A) +AYUV_X_WRAPPER(ayuv, A, Y, U, V) + #define output_pixel(pos, val, bits) \ AV_WL16(pos, av_clip_uintp2(val >> shift, bits) << output_shift); @@ -3379,6 +3391,11 @@ av_cold void ff_sws_init_output_funcs(SwsContext *c, case AV_PIX_FMT_AYUV64LE: *yuv2packedX = yuv2ayuv64le_X_c; break; + case AV_PIX_FMT_AYUV: + *yuv2packed1 = yuv2ayuv_1_c; + *yuv2packed2 = yuv2ayuv_2_c; + *yuv2packedX = yuv2ayuv_X_c; + break; case AV_PIX_FMT_VUYA: case AV_PIX_FMT_VUYX: *yuv2packed1 = yuv2vuyX_1_c; diff --git a/libswscale/utils.c b/libswscale/utils.c index e2ad71a38d..84d23c3ff2 100644 --- a/libswscale/utils.c +++ b/libswscale/utils.c @@ -268,7 +268,7 @@ static const FormatEntry format_entries[] = { [AV_PIX_FMT_RGBAF16LE] = { 1, 0 }, [AV_PIX_FMT_XV30LE] = { 1, 1 }, [AV_PIX_FMT_XV36LE] = { 1, 1 }, - [AV_PIX_FMT_AYUV] = { 1, 0 }, + [AV_PIX_FMT_AYUV] = { 1, 1 }, [AV_PIX_FMT_UYVA] = { 1, 0 }, [AV_PIX_FMT_VYU444] = { 1, 0 }, [AV_PIX_FMT_V30XLE] = { 1, 0 }, diff --git a/tests/ref/fate/filter-pixdesc-ayuv b/tests/ref/fate/filter-pixdesc-ayuv new file mode 100644 index 0000000000..178e847222 --- /dev/null +++ b/tests/ref/fate/filter-pixdesc-ayuv @@ -0,0 +1 @@ +pixdesc-ayuv a21ac760efdec0065bcf605f4ed75f7f diff --git a/tests/ref/fate/filter-pixfmts-copy b/tests/ref/fate/filter-pixfmts-copy index 120129dc1e..dc165b5ec5 100644 --- a/tests/ref/fate/filter-pixfmts-copy +++ b/tests/ref/fate/filter-pixfmts-copy @@ -2,6 +2,7 @@ 0rgb 527ef3d164c8fd0700493733959689c2 abgr 023ecf6396d324edb113e4a483b79ba2 argb f003b555ef429222005d33844cca9325 +ayuv eb7e43cfbb961d1e369311d0f58b9f52 ayuv64le 07b9c969dfbe4add4c0626773b151d4f bgr0 6fcd67c8e6cec723dab21c70cf53dc16 bgr24 4cff3814819f02ecf5824edfd768d2b1 diff --git a/tests/ref/fate/filter-pixfmts-crop b/tests/ref/fate/filter-pixfmts-crop index 4731e96fc0..07ded708bc 100644 --- a/tests/ref/fate/filter-pixfmts-crop +++ b/tests/ref/fate/filter-pixfmts-crop @@ -2,6 +2,7 @@ 0rgb 974833c777e6abe6d84dc59af2ca5625 abgr 1d21f5b8a20186ac9dd54459c986a2a7 argb 8b822972049a1e207000763f2564d6e0 +ayuv f2846cdd8fc01820e561fe4d3855938c ayuv64le ab2f7bc8f150af47c42c778e3ea28bce bgr0 38a84849a9198667c348c686802e3b52 bgr24 1dacd8e04bf0eff163e82250d01a9cc7 diff --git a/tests/ref/fate/filter-pixfmts-field b/tests/ref/fate/filter-pixfmts-field index 0727d733f2..9e1e06bd80 100644 --- a/tests/ref/fate/filter-pixfmts-field +++ b/tests/ref/fate/filter-pixfmts-field @@ -2,6 +2,7 @@ 0rgb e2c35753a2271d1f9455b1809bc0e907 abgr c0eb95959edf5d40ff8af315e62d0f8a argb 6dca4f2987b49b7d63f702d17bace630 +ayuv 6aeadbc3ec2a6ff2bfab9495e7285fed ayuv64le d9836decca6323ba88b3b3d02257c0b6 bgr0 1da3fdbac616b3b410d081e39ed7a1f6 bgr24 573c76d77b1cbe6534ea7c0267dc1b13 diff --git a/tests/ref/fate/filter-pixfmts-fieldorder b/tests/ref/fate/filter-pixfmts-fieldorder index 1d7a98ce11..8f1febf4ad 100644 --- a/tests/ref/fate/filter-pixfmts-fieldorder +++ b/tests/ref/fate/filter-pixfmts-fieldorder @@ -2,6 +2,7 @@ 0rgb 2b0f066cfa0bef378a492875d541de8f abgr 832924b5351361db68dbdbb96c60ae55 argb 80d08e68cb91bc8f2f817516e65f0bd0 +ayuv 61b23fc754d8ca0d6740fa08a0a6ebf2 ayuv64le 84ef6260fe02427da946d4a2207fb54c bgr0 d2c676224ea80ac3ce01afde325ea1a0 bgr24 b7fdbcd10f20e6ea2d40aae0f329f80d diff --git a/tests/ref/fate/filter-pixfmts-hflip b/tests/ref/fate/filter-pixfmts-hflip index 43404db154..a49abba15b 100644 --- a/tests/ref/fate/filter-pixfmts-hflip +++ b/tests/ref/fate/filter-pixfmts-hflip @@ -2,6 +2,7 @@ 0rgb ada57572ee2b35f86edac9b911ce8523 abgr d2da6c3ee72e4a89a7cd011dd08566b2 argb 36cf791c52c5463bfc52a070de54337e +ayuv 122f591eac5669b658c22b09355e4263 ayuv64le 4cedbc38b3d4dcb26cdab170ce6d667b bgr0 66e9fda4e658d73bfe4fc9d792542271 bgr24 db074979bd684ca4547e28681ad3f6ab diff --git a/tests/ref/fate/filter-pixfmts-il b/tests/ref/fate/filter-pixfmts-il index 4a6f15f074..1ac9cf3bd2 100644 --- a/tests/ref/fate/filter-pixfmts-il +++ b/tests/ref/fate/filter-pixfmts-il @@ -2,6 +2,7 @@ 0rgb 53efe0182723cd1dedfdbf56357c76f5 abgr 97603869e6248a8e5d8501563a11b114 argb 9e50e6ef02c83f28e97865a1f46ddfcd +ayuv 3dfdbbbf605d83629f3ef4c96210b074 ayuv64le 6f45f683e99ddf4180c7c7f47719efcc bgr0 590dcd1297d1dd4541eea217381db604 bgr24 73afe7b447b083a7c2d682abe8dd451a diff --git a/tests/ref/fate/filter-pixfmts-null b/tests/ref/fate/filter-pixfmts-null index 120129dc1e..dc165b5ec5 100644 --- a/tests/ref/fate/filter-pixfmts-null +++ b/tests/ref/fate/filter-pixfmts-null @@ -2,6 +2,7 @@ 0rgb 527ef3d164c8fd0700493733959689c2 abgr 023ecf6396d324edb113e4a483b79ba2 argb f003b555ef429222005d33844cca9325 +ayuv eb7e43cfbb961d1e369311d0f58b9f52 ayuv64le 07b9c969dfbe4add4c0626773b151d4f bgr0 6fcd67c8e6cec723dab21c70cf53dc16 bgr24 4cff3814819f02ecf5824edfd768d2b1 diff --git a/tests/ref/fate/filter-pixfmts-pad b/tests/ref/fate/filter-pixfmts-pad index abf4fceb46..5d8111b623 100644 --- a/tests/ref/fate/filter-pixfmts-pad +++ b/tests/ref/fate/filter-pixfmts-pad @@ -2,6 +2,7 @@ 0rgb 8e076dd0f8a9f4652595dffe3544f0f0 abgr 52738042432893de555e6a3833172806 argb 2a10108ac524b422b8a2393c064b3eab +ayuv ddb44f03af05b0cb01dced60641a4160 bgr0 025d4d5e5691801ba39bc9de70e39df0 bgr24 f8b65ad845905c7d0c93ca28dfbb826f bgr48le 4564b56dd1f2a9761b8a7a5244ac4c49 diff --git a/tests/ref/fate/filter-pixfmts-scale b/tests/ref/fate/filter-pixfmts-scale index 2052d3f2f0..41a6fe76e7 100644 --- a/tests/ref/fate/filter-pixfmts-scale +++ b/tests/ref/fate/filter-pixfmts-scale @@ -2,6 +2,7 @@ 0rgb 80a58af8c639743307207ab4b69ca863 abgr 63f2eaa8712ea6108985f4a0b83587c9 argb f0e17c71a40643c33a5bcfb481f6d8f8 +ayuv 9992b829065e2ea4a44de3a25766ca9b ayuv64le 59fb016f9874062d0be77cb3920ffed2 bgr0 243d58ca64f97b2f415b4c63cb79f0e1 bgr24 18744aaab4b8bce065a7144dc0ccf921 diff --git a/tests/ref/fate/filter-pixfmts-transpose b/tests/ref/fate/filter-pixfmts-transpose index 0a395f7e71..bcda0e6460 100644 --- a/tests/ref/fate/filter-pixfmts-transpose +++ b/tests/ref/fate/filter-pixfmts-transpose @@ -2,6 +2,7 @@ 0rgb cf1bedd0784a3efd3ab00c4e44005c37 abgr 6d6f896f853a6c6f93ee70dba9af3d17 argb 87bbd23debb94d486ac3a6b6c0b005f9 +ayuv fe3d4a2d4d37deb94e6f447edc77f199 ayuv64le e4c07e0d5b333b3bc9eb4f3ce6af3a2c bgr0 df3a6eedd4939ce09a357b655ac2962a bgr24 f9a08135e5d58c0b2a5509c369a88414 diff --git a/tests/ref/fate/filter-pixfmts-vflip b/tests/ref/fate/filter-pixfmts-vflip index 5ba28917a7..bb8ad46704 100644 --- a/tests/ref/fate/filter-pixfmts-vflip +++ b/tests/ref/fate/filter-pixfmts-vflip @@ -2,6 +2,7 @@ 0rgb 76b792f8ce8a72925e04294dc2f25b36 abgr 8b94f489e68802d76f1e2844688a4911 argb 3fd6af7ef2364d8aa845d45db289a04a +ayuv 928ac9b09b90dec1d8bc3ecd13b75a60 ayuv64le 558671dd31d0754cfa6344eaf441df78 bgr0 7117438cf000254610f23625265769b5 bgr24 52b2c21cbc166978a38a646c354b6858
Signed-off-by: James Almer <jamrial@gmail.com> --- libswscale/output.c | 323 ++++++++++++----------- libswscale/utils.c | 2 +- tests/ref/fate/filter-pixdesc-ayuv | 1 + tests/ref/fate/filter-pixfmts-copy | 1 + tests/ref/fate/filter-pixfmts-crop | 1 + tests/ref/fate/filter-pixfmts-field | 1 + tests/ref/fate/filter-pixfmts-fieldorder | 1 + tests/ref/fate/filter-pixfmts-hflip | 1 + tests/ref/fate/filter-pixfmts-il | 1 + tests/ref/fate/filter-pixfmts-null | 1 + tests/ref/fate/filter-pixfmts-pad | 1 + tests/ref/fate/filter-pixfmts-scale | 1 + tests/ref/fate/filter-pixfmts-transpose | 1 + tests/ref/fate/filter-pixfmts-vflip | 1 + 14 files changed, 183 insertions(+), 154 deletions(-) create mode 100644 tests/ref/fate/filter-pixdesc-ayuv