diff options
| author | Yunqing Wang <yunqingwang@google.com> | 2018-10-11 15:13:47 -0700 |
|---|---|---|
| committer | Yunqing Wang <yunqingwang@google.com> | 2018-10-12 00:02:34 +0000 |
| commit | e4f030be87735114f5e70ba45e006c1afbdd0872 (patch) | |
| tree | f4885fa2bda945826377518431ddcfcd3e352b14 /vpxenc.h | |
| parent | fbac7790a65595fe0582c4283c2389a0d1d2b7bd (diff) | |
| download | libvpx-e4f030be87735114f5e70ba45e006c1afbdd0872.tar libvpx-e4f030be87735114f5e70ba45e006c1afbdd0872.tar.gz libvpx-e4f030be87735114f5e70ba45e006c1afbdd0872.tar.bz2 libvpx-e4f030be87735114f5e70ba45e006c1afbdd0872.zip | |
Make 4-tap interp filter coefficients even numbers
This CL modified 4-tap interp filter coefficients to be even numbers,
which would help in writing 4-tap filter SIMD optimizations. The coding
performance change was negligible. Speed 1 borg test showed:
avg_psnr: ovr_psnr: ssim:
lowres: -0.003 -0.012 -0.017
midres: 0.029 0.018 0.043
hdres: 0.024 0.044 0.033
Change-Id: Id7c54bb9a9c1aee19c41bc6f1dc3b9682d158bba
Diffstat (limited to 'vpxenc.h')
0 files changed, 0 insertions, 0 deletions