diff options
author | Dr.Smile <vabnick@gmail.com> | 2021-03-09 04:21:53 +0300 |
---|---|---|
committer | Dr.Smile <vabnick@gmail.com> | 2021-04-21 20:58:01 +0300 |
commit | 904d9219395d8f471e949506feaa05fa18183f4e (patch) | |
tree | 1530817112a92b21e5d1f9e3130adea7cc099193 /libass/ass_func_template.h | |
parent | cb5263a55b79e45517f09ff19d8fcfa921deb94a (diff) | |
download | libass-904d9219395d8f471e949506feaa05fa18183f4e.tar.bz2 libass-904d9219395d8f471e949506feaa05fa18183f4e.tar.xz |
Rewrite add/sub_bitmaps() assembly
Change list:
- No special handling of unaligned case (removed in previous commit).
- Common macro for both add_bitmaps() and sub_bitmaps().
- Reduced register usage and efficient 32-bit version.
- add_bitmaps() no longer rely on zero padding.
- Vectorized handling of width tails (instead of byte loop
in sub_bitmaps(), great speedup for non-empty tails).
Diffstat (limited to 'libass/ass_func_template.h')
-rw-r--r-- | libass/ass_func_template.h | 3 |
1 files changed, 1 insertions, 2 deletions
diff --git a/libass/ass_func_template.h b/libass/ass_func_template.h index 79ca3a6..4737b87 100644 --- a/libass/ass_func_template.h +++ b/libass/ass_func_template.h @@ -105,11 +105,10 @@ const BitmapEngine DECORATE(bitmap_engine) = { #endif .add_bitmaps = DECORATE(add_bitmaps), -#ifdef __x86_64__ .sub_bitmaps = DECORATE(sub_bitmaps), +#ifdef __x86_64__ .mul_bitmaps = DECORATE(mul_bitmaps), #else - .sub_bitmaps = ass_sub_bitmaps_c, .mul_bitmaps = ass_mul_bitmaps_c, #endif |