diff options
author | reimar <reimar@b3059339-0415-0410-9bf9-f77b7e298cf2> | 2007-11-18 18:33:45 +0000 |
---|---|---|
committer | reimar <reimar@b3059339-0415-0410-9bf9-f77b7e298cf2> | 2007-11-18 18:33:45 +0000 |
commit | 13a205e0757fd9a6797c326017b7616b0201e994 (patch) | |
tree | c5523a93875fe1cc5ad7637de51f327013b6df95 | |
parent | 66c47599923f2919756423d47f32f2186d15cef9 (diff) | |
download | mpv-13a205e0757fd9a6797c326017b7616b0201e994.tar.bz2 mpv-13a205e0757fd9a6797c326017b7616b0201e994.tar.xz |
100l, *ppc++ was supposed to be replaced by ppc[i] in r25100, but that is not any faster.
Just removing the += s->samples_overlap - s->num_channels; still provides a
ca. 20% speedup on x86 (AThlon X2 64) with gcc 3.4 (compiler stupidity?)
git-svn-id: svn://svn.mplayerhq.hu/mplayer/trunk@25102 b3059339-0415-0410-9bf9-f77b7e298cf2
-rw-r--r-- | libaf/af_scaletempo.c | 2 |
1 files changed, 0 insertions, 2 deletions
diff --git a/libaf/af_scaletempo.c b/libaf/af_scaletempo.c index 19f15699d1..90f781f655 100644 --- a/libaf/af_scaletempo.c +++ b/libaf/af_scaletempo.c @@ -171,8 +171,6 @@ static int best_overlap_offset_s16(af_scaletempo_t* s) int32_t corr = 0; int16_t* ps = search_start; ppc = s->buf_pre_corr; - ppc += s->samples_overlap - s->num_channels; - ps += s->samples_overlap - s->num_channels; i = -(s->samples_overlap - s->num_channels); do { corr += ( *ppc++ * *ps++ ) >> s->shift_corr; |