github.com/videolan/dav1d.git - Unnamed repository; edit this file 'description' to name the repository.

Age	Commit message (Collapse)	Author
2021-12-13	x86: Add 10-bit sgr AVX-512 (Ice Lake) asm	Henrik Gramner

2021-10-29	Remove lpf_stride parameter from LR filters	Victorien Le Couviour--Tuffet

2021-10-29	Allow CDEF and LR to run sbrows in parallel	Victorien Le Couviour--Tuffet

2021-09-10	Revert "Group lr_lpf_line re-allocation with lr_mask_sz"	Victorien Le Couviour--Tuffet
	This reverts commit e53314177a5a45a1c1c907464b19ade625d110a6. Causes issues when the sample has both 8 and 16 bit content. Credit to Oss-Fuzz.
2021-09-07	Group lr_lpf_line re-allocation with lr_mask_sz	Victorien Le Couviour--Tuffet

2021-09-03	Merge the 3 threading models into a single one	Victorien Le Couviour--Tuffet
	Merges the 3 threading parameters into a single `--threads=` argument. Frame threading can still be controlled via the `--framedelay=` argument. Internally, the threading model is now a global thread/task pool design. Co-authored-by: Ronald S. Bultje <rsbultje@gmail.com>
2021-02-11	Add minor SGR optimizations	Henrik Gramner
	Split the 5x5, 3x3, and mix cases into separate functions. Shrink some tables. Move some scalar calculations out of the DSP function. Make Wiener and SGR share the same function prototype to eliminate a branch in lr_stripe().
2021-01-28	Add post-filters threading model	Victorien Le Couviour--Tuffet

2020-12-13	x86: Rewrite wiener SSE2/SSSE3/AVX2 asm	Henrik Gramner
	The previous implementation did two separate passes in the horizontal and vertical directions, with the intermediate values being stored in a buffer on the stack. This caused bad cache thrashing. By interleaving the horizontal and vertical passes in combination with a ring buffer for storing only a few rows at a time the performance is improved by a significant amount. Also split the function into 7-tap and 5-tap versions. The latter is faster and fairly common (always for chroma, sometimes for luma).
2020-12-13	Add miscellaneous minor wiener optimizations	Henrik Gramner
	Combine horizontal and vertical filter pointers into a single parameter when calling the wiener DSP function. Eliminate the +128 filter coefficient handling where possible.
2020-04-02	Skip loop restoration cache buffer resize for too-small buffers	Ronald S. Bultje
	Fixes crashes in dav1d_resize_{avx2,ssse3} on very small resolutions with super_res enabled but skipped because the width is too small.
2020-03-31	Invert src_w/h argument in mc.resize()	Ronald S. Bultje

2019-10-08	Remove branch when changing bit in LR edges mask	Luc Trudeau

2019-10-07	Don't backup pixels if next restoration unit is NONE	Luc Trudeau

2019-10-04	Check for RESTORATION_NONE once per frame	Luc Trudeau
	Prior checks were done at the sbrow level. This now allows to call dav1d_lr_sbrow and dav1d_lr_copy_lpf only when there's something for them to do.
2019-07-02	Reduce the size of frame threading buffers	Henrik Gramner
	Avoid allocating significantly more memory than what is actually used.
2019-02-08	Avoid warnings about variables being truncated by changing the type of variables	Martin Storsjö

2018-12-21	Duplicate LR line if the bottom edge only has one line available	Ronald S. Bultje
	Fixes #227.
2018-12-06	12 bits/component support	Ronald S. Bultje

2018-11-30	backup_lpf: increment row by the correct stripe_h	Janne Grunau
	Fixes #200.
2018-11-25	Move Av1FrameHeader and Av1SequenceHeader into public headers	Ronald S. Bultje
	Add DAV1D_/Dav1d prefix to everything.
2018-11-25	Make frame_hdr a pointer	Ronald S. Bultje

2018-11-25	Make sequence header a referenced object	Ronald S. Bultje

2018-11-24	backup_lpf: do not store 4 pixels rows at the bottom edge of the picture	Janne Grunau
	Fixes #192, an use-of-uninitialized-value in resize_c with clusterfuzz-testcase-minimized-dav1d_fuzzer-5657755306688512. Credits to oss-fuzz.
2018-11-19	Slightly simplify the loop in lr_sbrow()	Ronald S. Bultje

2018-11-17	Fix calculation of unit_idx to identify Av1RestorationUnit	Ronald S. Bultje
	ruy and rux are in unit_size dimensions, whereas lr_mask are in sb128 dimensions, and unit_idx is in sb64 dimensions, so one can't be derived from the other. Instead, remove ruy/rux and derive unit_idx and sb_idx directly from the block positions aligned to the unit_size.
2018-11-16	Add support for super-res	Ronald S. Bultje
	Fixes #172.
2018-10-28	Backup extra 8 pixels at bottom of frame	Ronald S. Bultje
	Fixes #112.
2018-10-25	Build: Add suffix to templated BITDEPTH files	Marvin Scholz
	Fix #96