... | @@ -29,7 +29,7 @@ Removing redundancies: |
... | @@ -29,7 +29,7 @@ Removing redundancies: |
|
Other speed optimizations:
|
|
Other speed optimizations:
|
|
- film-grain GL shader (like [placebo](https://github.com/haasn/libplacebo/blob/master/src/shaders/av1.c));
|
|
- film-grain GL shader (like [placebo](https://github.com/haasn/libplacebo/blob/master/src/shaders/av1.c));
|
|
- get rid of `memset(0)` of seq_hdr and frame_hdr after allocation.
|
|
- get rid of `memset(0)` of seq_hdr and frame_hdr after allocation.
|
|
- Reuse per-frame buffers when possible instead of freeing and reallocating them all the time. Applicable to (in order of importance) `picture_alloc_with_edges()`, `dav1d_submit_frame()`, `dav1d_cdf_thread_alloc()`, and `dav1d_parse_obus()`.
|
|
- Reuse per-frame buffers when possible instead of freeing and reallocating them all the time. Applicable to (in order of importance) ~~`picture_alloc_with_edges()`~~, `dav1d_submit_frame()`, `dav1d_cdf_thread_alloc()`, and `dav1d_parse_obus()`.
|
|
|
|
|
|
Cleanups:
|
|
Cleanups:
|
|
- palette buffers are always 16-bit, even if content is 8-bit (remaining item in #257);
|
|
- palette buffers are always 16-bit, even if content is 8-bit (remaining item in #257);
|
... | | ... | |