diff options
| author | Graham Booker <gbooker@tamu.edu> | 2007-06-16 18:59:10 +0000 |
|---|---|---|
| committer | Guillaume Poirier <gpoirier@mplayerhq.hu> | 2007-06-16 18:59:10 +0000 |
| commit | f4a02f6e9bc0901fd9b21544f34e36c93ba9cfc1 (patch) | |
| tree | d91d8fc0ca152ce1475cdab6b23c09d2b679d709 /libavcodec/ppc/h264_altivec.c | |
| parent | a444671542226b5f977351cabb6fa6ddaf5afd34 (diff) | |
| download | ffmpeg-f4a02f6e9bc0901fd9b21544f34e36c93ba9cfc1.tar.gz | |
Use a faster way to compute 255-val: Instead of creating a vector of
all 255s, and then doing the subtraction, nor of the vector with itself: saves
one instruction and a register.
Patch by Graham Booker % gbooker A tamu P edu%
Originally committed as revision 9340 to svn://svn.ffmpeg.org/ffmpeg/trunk
Diffstat (limited to 'libavcodec/ppc/h264_altivec.c')
| -rw-r--r-- | libavcodec/ppc/h264_altivec.c | 6 |
1 files changed, 2 insertions, 4 deletions
diff --git a/libavcodec/ppc/h264_altivec.c b/libavcodec/ppc/h264_altivec.c index 9055d73e7f..9eccf2873d 100644 --- a/libavcodec/ppc/h264_altivec.c +++ b/libavcodec/ppc/h264_altivec.c @@ -766,7 +766,6 @@ static inline vector unsigned char h264_deblock_mask ( register vector unsigned const vector unsigned char A0v = vec_sl(vec_splat_u8(10), vec_splat_u8(4)); \ \ register vector unsigned char pq0bit = vec_xor(p0,q0); \ - register vector unsigned char temp; \ register vector unsigned char q1minus; \ register vector unsigned char p0minus; \ register vector unsigned char stage1; \ @@ -775,11 +774,10 @@ static inline vector unsigned char h264_deblock_mask ( register vector unsigned register vector unsigned char delta; \ register vector unsigned char deltaneg; \ \ - temp = (vector unsigned char)vec_cmpeq(p0, p0); \ - q1minus = vec_xor(temp, q1); /* 255 - q1 */ \ + q1minus = vec_nor(q1, q1); /* 255 - q1 */ \ stage1 = vec_avg(p1, q1minus); /* (p1 - q1 + 256)>>1 */ \ stage2 = vec_sr(stage1, vec_splat_u8(1)); /* (p1 - q1 + 256)>>2 = 64 + (p1 - q1) >> 2 */ \ - p0minus = vec_xor(temp, p0); /* 255 - p0 */ \ + p0minus = vec_nor(p0, p0); /* 255 - p0 */ \ stage1 = vec_avg(q0, p0minus); /* (q0 - p0 + 256)>>1 */ \ pq0bit = vec_and(pq0bit, vec_splat_u8(1)); \ stage2 = vec_avg(stage2, pq0bit); /* 32 + ((q0 - p0)&1 + (p1 - q1) >> 2 + 1) >> 1 */ \ |