shithub: dav1d

Info  •  Files  •  Log  •  Branches

7cf5d753 – Martin Storsjö <martin@martin.st> authored on 2020/02/09 18:39

arm64: looprestoration: Prepare for 16 bpc by splitting code to separate files

32e265a8 – Martin Storsjö <martin@martin.st> authored on 2020/02/10 05:02

arm: looprestoration: Add 8bpc to existing function names, add HIGHBD_*_SUFFIX

96da9cc2 – Martin Storsjö <martin@martin.st> authored on 2020/02/04 16:03

looprestoration: Add a bpc parameter to the init func

8fb30657 – Martin Storsjö <martin@martin.st> authored on 2020/02/09 18:14

arm: looprestoration: Improve scheduling in box3/5_h slightly

8e8fb84d – Martin Storsjö <martin@martin.st> authored on 2020/02/05 05:17

arm: Use int16_t for the tmp intermediate buffer

feeaf785 – Martin Storsjö <martin@martin.st> authored on 2020/02/06 18:45

arm: looprestoration: Fix a comment

e4208e85 – Jean-Baptiste Kempf <jb@videolan.org> authored on 2020/02/10 16:19

NEWS: Official naming is AVX2, not AVX-2

d4c5ad49 – Martin Storsjö <martin@martin.st> authored and Janne Grunau <janne-vlc@jannau.net> committed on 2020/02/01 09:34

arm64: mc: Reduce the width of a register copy

b1167ce1 – Martin Storsjö <martin@martin.st> authored and Janne Grunau <janne-vlc@jannau.net> committed on 2020/02/01 09:33

arm64: mc: Use two regs for alternating output rows for w4/8 in avg/w_avg/mask

0bad117e – Martin Storsjö <martin@martin.st> authored and Janne Grunau <janne-vlc@jannau.net> committed on 2020/02/01 09:33

arm64: mc: Simplify avg/w_avg/mask by always using the w16 macro

2e68c1f3 – Jean-Baptiste Kempf <jb@videolan.org> authored on 2020/02/09 09:35

Update NEWS for 0.6.0

8974c155 – Martin Storsjö <martin@martin.st> authored on 2020/02/06 04:36

arm64: mc: NEON implementation of warp for 16 bpc

e6cebeb7 – Martin Storsjö <martin@martin.st> authored on 2020/02/06 04:10

arm64: cdef: Add NEON implementations of CDEF for 16 bpc

1d5ef8df – Martin Storsjö <martin@martin.st> authored on 2020/02/06 04:09

arm: cdef: Prepare for 16bpc

19ce77e0 – Henrik Gramner <gramner@twoorioles.com> authored on 2020/01/28 12:42

x86: Add cdef_filter_4x4 AVX-512 (Ice Lake) asm

58a4ba07 – Henrik Gramner <gramner@twoorioles.com> authored on 2020/02/05 22:43

Reorder the Dav1dFrameHeader struct to fix alignment issues

c89eb564 – Martin Storsjö <martin@martin.st> authored on 2020/02/05 05:43

arm64: looprestoration: NEON implementation of wiener filter for 16 bpc

c2a2e6ee – Martin Storsjö <martin@martin.st> authored on 2020/02/05 05:43

arm: looprestoration: Fix the wiener C wrapper function for high bitdepths

5bc8a500 – Martin Storsjö <martin@martin.st> authored on 2020/02/05 05:43

arm: looprestoration: Prepare for 16bpc wiener filter by adding _8bpc to function names

2653292c – Martin Storsjö <martin@martin.st> authored on 2020/02/05 05:43

arm: looprestoration: Clarify a comment

fe44861b – Martin Storsjö <martin@martin.st> authored on 2020/02/04 06:50

arm64: mc: NEON implementation of put/prep 8tap/bilin for 16 bpc

c851c65c – kossh1 <jonvito16@gmail.com> authored and Ronald S. Bultje <rsbultje@gmail.com> committed on 2020/02/05 14:41

Update README

3c8110a9 – Lynne <dev@lynne.ee> authored on 2020/01/13 06:06

x86/msac: add an avx2 version for msac_decode_symbol_adapt16

35ab85bb – Lynne <dev@lynne.ee> authored on 2020/01/13 06:05

msac: make symbol_adapt16 a function pointer on x86_64

03511f8c – Martin Storsjö <martin@martin.st> authored on 2020/01/31 17:35

arm64: mc: NEON implementation of avg/mask/w_avg for 16 bpc

a285204a – Martin Storsjö <martin@martin.st> authored on 2020/01/31 17:35

arm: mc: Prepare the init file for higher bitdepths

7eaa7c9f – Martin Storsjö <martin@martin.st> authored on 2020/02/01 18:17

arm: Make the existing 8bpc assembly only built if 8bpc is enabled

b8399319 – Henrik Gramner <gramner@twoorioles.com> authored and Henrik Gramner <henrik@gramner.com> committed on 2020/02/03 18:56

x86: Avoid cmov instructions that depends on multiple flags

d21dc801 – Henrik Gramner <gramner@twoorioles.com> authored and Henrik Gramner <henrik@gramner.com> committed on 2020/02/03 18:56

x86: Add miscellaneous minor scalar optimizations

81a26458 – Henrik Gramner <gramner@twoorioles.com> authored and Henrik Gramner <henrik@gramner.com> committed on 2020/02/03 18:55

x86: Use unsigned pointer comparisons

bb178db0 – Henrik Gramner <gramner@twoorioles.com> authored on 2020/01/29 09:17

Rework the CDEF top edge handling

dccc21b7 – Henrik Gramner <gramner@twoorioles.com> authored on 2020/01/31 12:57

checkasm: Fix missing shift in high bit-depth cdef_filter test

fbc1b420 – Henrik Gramner <gramner@twoorioles.com> authored on 2020/02/01 09:17

Avoid masking the lsb in high bit-depth stride calculations

9c29f229 – Henrik Gramner <gramner@twoorioles.com> authored on 2020/01/24 15:34

checkasm: Increase buffer alignment to 64-byte on x86-64

361a3c8e – Martin Storsjö <martin@martin.st> authored on 2020/01/28 06:07

arm: cdef: Add special cased versions for pri_strength/sec_strength being zero

6ad9bd5f – Martin Storsjö <martin@martin.st> authored on 2020/01/28 05:30

arm: cdef: Fix some comment typos

ba23ac8c – Henrik Gramner <gramner@twoorioles.com> authored and Henrik Gramner <henrik@gramner.com> committed on 2020/01/28 18:49

Fix crash in dav1d_apply_grain() with negative picture strides

eaaf2218 – Henrik Gramner <gramner@twoorioles.com> authored and Henrik Gramner <henrik@gramner.com> committed on 2020/01/27 12:42

Optimize the cdef_filter C implementation

fad6db20 – Henrik Gramner <gramner@twoorioles.com> authored and Henrik Gramner <henrik@gramner.com> committed on 2020/01/27 12:41

checkasm: Improve cdef_filter test

6385cde2 – Henrik Gramner <gramner@twoorioles.com> authored and Henrik Gramner <henrik@gramner.com> committed on 2020/01/24 14:40

Avoid redundant calls to CDEF DSP functions

447b7c63 – Henrik Gramner <gramner@twoorioles.com> authored on 2020/01/21 19:10

x86: Bump nasm version requirement to 2.14

e636a2f4 – Konstantin Pavlov <thresh@videolan.org> authored on 2020/01/21 16:25

CI: Use a newer image to build snap packages

e706fac9 – Victorien Le Couviour--Tuffet <victorien@videolan.org> authored and Victorien Le Couviour--Tuffet <psilokos@twoorioles.com> committed on 2019/12/11 19:25

x86: add prep_8tap AVX512 asm

b83cb964 – Victorien Le Couviour--Tuffet <victorien@videolan.org> authored and Victorien Le Couviour--Tuffet <psilokos@twoorioles.com> committed on 2020/01/17 08:42

x86: replace "mov hb, Xb" by "movzx hd, Xb" in MC

289ca2ce – Victorien Le Couviour--Tuffet <psilokos@twoorioles.com> authored on 2020/01/20 05:35

x86inc: save xmm_regs_used in spill_xmm for non-win64

010eae8b – Martin Storsjö <martin@martin.st> authored on 2020/01/15 07:41

arm64: itx: Fix overflow/clipping in negation in idct16

ef64567e – Henrik Gramner <gramner@twoorioles.com> authored and Henrik Gramner <henrik@gramner.com> committed on 2020/01/14 16:53

x86: Fix overflows in SSSE3 idct

3a3af969 – Henrik Gramner <gramner@twoorioles.com> authored and Henrik Gramner <henrik@gramner.com> committed on 2020/01/14 15:52

x86: Fix missing saturations in inverse identity asm

8ff89463 – Ronald S. Bultje <rsbultje@gmail.com> authored on 2019/12/21 11:06

SSSE3 implementations of film grain

e79e5ceb – Dale Curtis <dalecurtis@chromium.org> authored on 2020/01/10 08:57

Reduce scope of NO_SANITIZE usage

c192e0db – Henrik Gramner <gramner@twoorioles.com> authored and Henrik Gramner <henrik@gramner.com> committed on 2020/01/09 12:29

Add a workaround for -fsanitize=cfi + dlsym() issue

5462c2a8 – Victorien Le Couviour--Tuffet <victorien@videolan.org> authored and Ronald S. Bultje <rsbultje@gmail.com> committed on 2019/12/11 19:24

x86: add prep_bilin AVX512 asm

40891aab – Victorien Le Couviour--Tuffet <victorien@videolan.org> authored and Ronald S. Bultje <rsbultje@gmail.com> committed on 2019/12/18 11:01

x86: add avx512icl cpu flag to x86inc.asm

430967a6 – Victorien Le Couviour--Tuffet <victorien@videolan.org> authored and Ronald S. Bultje <rsbultje@gmail.com> committed on 2019/10/29 12:19

checkasm: x86: ensure all SIMD lanes are turned on at all times

a4721225 – Henrik Gramner <gramner@twoorioles.com> authored and Henrik Gramner <henrik@gramner.com> committed on 2020/01/07 19:44

Add misc. inverse transform C optimizations

c37b5ee3 – Henrik Gramner <gramner@twoorioles.com> authored and Henrik Gramner <henrik@gramner.com> committed on 2020/01/07 19:44

Skip clipping in the inverse wht transform C implementation

a7ca7b22 – Henrik Gramner <gramner@twoorioles.com> authored and Henrik Gramner <henrik@gramner.com> committed on 2020/01/07 19:44

x86: Fix SSSE3 inverse identity transform overflow/clipping

f16b43cd – Henrik Gramner <gramner@twoorioles.com> authored and Henrik Gramner <henrik@gramner.com> committed on 2020/01/07 19:43

x86: Fix AVX2 inverse identity transform overflow/clipping

50220456 – Xavier Claessens <xavier.claessens@collabora.com> authored and Xavier Claessens <xclaesse@gmail.com> committed on 2019/12/30 14:58

Fix building as a meson subproject

115fe773 – Dale Curtis <dalecurtis@google.com> authored and Dale Curtis <dalecurtis@chromium.org> committed on 2020/01/07 18:56

Fix missing include for limits.h

8d574f70 – Martin Storsjö <martin@martin.st> authored on 2020/01/04 19:41

arm64: msac: Avoid 32 bit intermediates in symbol_adapt

9f084b0d – Martin Storsjö <martin@martin.st> authored on 2020/01/02 10:43

arm64: itx: Use sqrdmulh in the preexisting identity transform functions

e36088e4 – Martin Storsjö <martin@martin.st> authored on 2020/01/01 18:12

arm64: itx: Specialcase transforms with identity in the first pass with downshift

33e65d80 – Martin Storsjö <martin@martin.st> authored on 2020/01/02 02:58

arm64: itx: Adjust .irp in the 4x16/16x4/8x16/16x8 functions

4504ae3f – Ronald S. Bultje <rsbultje@gmail.com> authored on 2019/12/31 14:46

Don't interleave the skip mode index finding loops

3d166b97 – Ronald S. Bultje <rsbultje@gmail.com> authored on 2020/01/01 12:42

Prevent shift by >= 32

acadacfa – Ronald S. Bultje <rsbultje@gmail.com> authored on 2019/12/31 14:46

Take lossless into account when assigning loopfilter strength

de6e3170 – Ronald S. Bultje <rsbultje@gmail.com> authored on 2019/12/31 07:15

Deal with chroma coefficients that are exactly 0x100000

f306f969 – Henrik Gramner <gramner@twoorioles.com> authored and Henrik Gramner <henrik@gramner.com> committed on 2019/12/30 23:14

x86: Fix inverse (flip)adst 8x4 clipping

81aba493 – Henrik Gramner <gramner@twoorioles.com> authored and Henrik Gramner <henrik@gramner.com> committed on 2019/12/30 23:13

Fix C inverse ADST clipping

a4178cc2 – Ronald S. Bultje <rsbultje@gmail.com> authored on 2019/12/28 10:12

av1: use chroma txtp inference over default DCT_DCT if qidx=0

1d36922f – Ronald S. Bultje <rsbultje@gmail.com> authored and James Almer <jamrial@gmail.com> committed on 2019/12/28 10:04

av1: skip super-resolution upscaling if width < 16

7aea6858 – Ronald S. Bultje <rsbultje@gmail.com> authored on 2019/12/28 12:00

av1: do C inverse transforms in int32_t precision

cdf4a3bc – Michael Bradshaw <mjbshaw@google.com> authored and Ronald S. Bultje <rsbultje@gmail.com> committed on 2019/12/28 17:26

Allow skip mode

dfcd6ea9 – Michael Bradshaw <mjbshaw@google.com> authored and Ronald S. Bultje <rsbultje@gmail.com> committed on 2019/12/28 17:04

Disable warping on scaled references

a57b0777 – Ronald S. Bultje <rsbultje@gmail.com> authored on 2019/12/23 10:30

Check skip flag before setting tx context to TX_4X4 in lossless frames

14d586ac – Martin Storsjö <martin@martin.st> authored on 2019/12/18 05:18

Don't assume dlsym exists on linux

6b611d36 – Henrik Gramner <gramner@twoorioles.com> authored on 2019/12/12 18:09

Linux: Add a workaround for a glibc stack size issue

eb211838 – Henrik Gramner <gramner@twoorioles.com> authored and Henrik Gramner <henrik@gramner.com> committed on 2019/12/14 16:48

x86: Disable AVX-512 by default

2d608a5f – Henrik Gramner <gramner@twoorioles.com> authored and Henrik Gramner <henrik@gramner.com> committed on 2019/12/14 11:02

Fix potential race condition in dav1d_get_cpu_flags()

7b208fa8 – Henrik Gramner <gramner@twoorioles.com> authored and Henrik Gramner <henrik@gramner.com> committed on 2019/12/14 10:53

x86: Remove unused cpu flags

481c0592 – Ewout ter Hoeven <e.m.terhoeven@student.tudelft.nl> authored and Henrik Gramner <gramner@twoorioles.com> committed on 2019/12/14 16:34

Add support for Ice Lake AVX-512 cpu flags

003f17d8 – Raphaël Zumer <rzumer@tebako.net> authored on 2019/12/13 17:09

Correct the edge buffer documentation

9bd31820 – Luc Trudeau <ltrudeau@twoorioles.com> authored on 2019/12/05 10:06

Move lvl variable in cdef_brow to outer loop

562f1958 – Ronald S. Bultje <rsbultje@gmail.com> authored on 2019/11/03 02:52

Simplify shifting in generate_grain_y/uv AVX2

940eee48 – Henrik Gramner <gramner@twoorioles.com> authored and Henrik Gramner <henrik@gramner.com> committed on 2019/12/05 14:33

Avoid adding offsets to NULL chroma pointers in 4:0:0

39667c75 – Jean-Baptiste Kempf <jb@videolan.org> authored on 2019/12/02 13:19

Update NEWS

162ba33d – Martin Storsjö <martin@martin.st> authored on 2019/11/30 19:09

arm: 32: ipred: Fix assembling with older binutils

82eda83a – Henrik Gramner <gramner@twoorioles.com> authored and Henrik Gramner <henrik@gramner.com> committed on 2019/11/22 15:50

Avoid excessive L2 collisions with certain frame widths

2e5e05b7 – Janne Grunau <janne-vlc@jannau.net> authored and Henrik Gramner <gramner@twoorioles.com> committed on 2019/11/25 00:35

build: do not error out if clock_gettime is not found on darwin

fc6c2578 – Henrik Gramner <gramner@twoorioles.com> authored on 2019/11/22 12:34

Specify inlining decisions for common ipred_z C functions

246c2803 – Justin Bull <me@justinbull.ca> authored and Henrik Gramner <gramner@twoorioles.com> committed on 2019/11/26 17:40

cli: Return only EXIT_SUCCESS or EXIT_FAILURE from main

f59b5713 – Henrik Gramner <gramner@twoorioles.com> authored and Jean-Baptiste Kempf <jb@videolan.org> committed on 2019/11/22 21:29

tools: simplify get_seed on macOS

a52459b3 – Jan Beich <jbeich@FreeBSD.org> authored and Jean-Baptiste Kempf <jb@videolan.org> committed on 2019/07/29 14:37

checkasm: replace gettimeofday with clock_gettime

cf4b381a – Jan Beich <jbeich@FreeBSD.org> authored and Jean-Baptiste Kempf <jb@videolan.org> committed on 2019/11/22 17:06

tools: prefer mach_absolute_time on macOS for forward compatibility

eaa3be9a – Jan Beich <jbeich@FreeBSD.org> authored and Jean-Baptiste Kempf <jb@videolan.org> committed on 2019/11/22 17:05

tools: mach_absolute_time is not portable, so stop checking at configure

b9a43c60 – Luc Trudeau <ltrudeau@twoorioles.com> authored and Jean-Baptiste Kempf <jb@videolan.org> committed on 2019/11/21 11:48

Avoid adding offsets to NULL pointers

5e8eccf2 – Konstantin Pavlov <thresh@videolan.org> authored and Jean-Baptiste Kempf <jb@videolan.org> committed on 2019/11/22 18:22

snap: bump grade to stable

59a28b19 – Henrik Gramner <gramner@twoorioles.com> authored and Henrik Gramner <henrik@gramner.com> committed on 2019/11/22 22:01

input: Use EIO instead of ENODATA

52c7427e – Martin Storsjö <martin@martin.st> authored on 2019/11/22 03:32

annexb: Cast size_t to int before adding to an int