[FFmpeg-cvslog] lavfi/gradfun: fix rounding in MMX code.

[Clément Bœsch]

ffmpeg | branch: master | Clément Bœsch <ubitux at gmail.com> | Fri Dec  7 00:36:29 2012 +0100| [49de902a1e074133583dd5d8599aa057ed1d1485] | committer: Clément Bœsch

lavfi/gradfun: fix rounding in MMX code.

Current code divide before increasing precision.

> http://git.videolan.org/gitweb.cgi/ffmpeg.git/?a=commit;h=49de902a1e074133583dd5d8599aa057ed1d1485
---

 libavfilter/x86/gradfun.c |    2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/libavfilter/x86/gradfun.c b/libavfilter/x86/gradfun.c
index 5e71aab..1ca5928 100644
--- a/libavfilter/x86/gradfun.c
+++ b/libavfilter/x86/gradfun.c
@@ -62,8 +62,8 @@ static void gradfun_filter_line_mmxext(uint8_t *dst, const uint8_t *src, const u
         "pminsw     %%mm7, %%mm2 \n" // m = -max(0, 127-m)
         "pmullw     %%mm2, %%mm2 \n"
         "paddw      %%mm4, %%mm0 \n" // pix += dither
-        "pmulhw     %%mm2, %%mm1 \n"
         "psllw         $2, %%mm1 \n" // m = m*m*delta >> 14
+        "pmulhw     %%mm2, %%mm1 \n"
         "paddw      %%mm1, %%mm0 \n" // pix += m
         "psraw         $7, %%mm0 \n"
         "packuswb   %%mm0, %%mm0 \n"