[FFmpeg-devel] [PATCH 06/21] swscale/output: add AYUV output support
James Almer
jamrial at gmail.com
Sat Oct 12 01:54:48 EEST 2024
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 at 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.
-------------- next part --------------
A non-text attachment was scrubbed...
Name: OpenPGP_signature.asc
Type: application/pgp-signature
Size: 495 bytes
Desc: OpenPGP digital signature
URL: <https://ffmpeg.org/pipermail/ffmpeg-devel/attachments/20241011/0924f2d2/attachment.sig>
More information about the ffmpeg-devel
mailing list