Commit c3a3d344 authored by Michael Niedermayer's avatar Michael Niedermayer

Alternative and faster (on gcc x86) plane rotation.

Originally committed as revision 12237 to svn://svn.ffmpeg.org/ffmpeg/trunk
parent 8af4d0fc
...@@ -107,9 +107,14 @@ static av_always_inline void row_fdct(FLOAT temp[64], DCTELEM * data) ...@@ -107,9 +107,14 @@ static av_always_inline void row_fdct(FLOAT temp[64], DCTELEM * data)
tmp5 += tmp6; tmp5 += tmp6;
tmp6 += tmp7; tmp6 += tmp7;
#if 0
z5= (tmp4 - tmp6) * A5; z5= (tmp4 - tmp6) * A5;
z2= tmp4*A2 + z5; z2= tmp4*A2 + z5;
z4= tmp6*A4 + z5; z4= tmp6*A4 + z5;
#else
z2= tmp4*(A2+A5) - tmp6*A5;
z4= tmp6*(A4-A5) + tmp4*A5;
#endif
tmp5*=A1; tmp5*=A1;
z11= tmp7 + tmp5; z11= tmp7 + tmp5;
...@@ -161,9 +166,14 @@ void ff_faandct(DCTELEM * data) ...@@ -161,9 +166,14 @@ void ff_faandct(DCTELEM * data)
tmp5 += tmp6; tmp5 += tmp6;
tmp6 += tmp7; tmp6 += tmp7;
#if 0
z5= (tmp4 - tmp6) * A5; z5= (tmp4 - tmp6) * A5;
z2= tmp4*A2 + z5; z2= tmp4*A2 + z5;
z4= tmp6*A4 + z5; z4= tmp6*A4 + z5;
#else
z2= tmp4*(A2+A5) - tmp6*A5;
z4= tmp6*(A4-A5) + tmp4*A5;
#endif
tmp5*=A1; tmp5*=A1;
z11= tmp7 + tmp5; z11= tmp7 + tmp5;
......
Markdown is supported
0% or
You are about to add 0 people to the discussion. Proceed with caution.
Finish editing this message first!
Please register or to comment