checkasm --bench on a Qualcomm Kryo (Sanpdragon 820):
nop: 33.0
avg_w4_8bpc_c: 450.5
avg_w4_8bpc_neon: 20.1
avg_w8_8bpc_c: 438.6
avg_w8_8bpc_neon: 45.2
avg_w16_8bpc_c: 1003.7
avg_w16_8bpc_neon: 112.8
avg_w32_8bpc_c: 3249.6
avg_w32_8bpc_neon: 429.9
avg_w64_8bpc_c: 7213.3
avg_w64_8bpc_neon: 1299.4
avg_w128_8bpc_c: 16791.3
avg_w128_8bpc_neon: 2978.4
w_avg_w4_8bpc_c: 605.7
w_avg_w4_8bpc_neon: 30.9
w_avg_w8_8bpc_c: 545.8
w_avg_w8_8bpc_neon: 72.9
w_avg_w16_8bpc_c: 1430.1
w_avg_w16_8bpc_neon: 193.5
w_avg_w32_8bpc_c: 4876.3
w_avg_w32_8bpc_neon: 715.3
w_avg_w64_8bpc_c: 11338.0
w_avg_w64_8bpc_neon: 2147.0
w_avg_w128_8bpc_c: 26822.0
w_avg_w128_8bpc_neon: 4596.3
mask_w4_8bpc_c: 604.6
mask_w4_8bpc_neon: 37.2
mask_w8_8bpc_c: 654.8
mask_w8_8bpc_neon: 96.0
mask_w16_8bpc_c: 1663.0
mask_w16_8bpc_neon: 272.4
mask_w32_8bpc_c: 5707.6
mask_w32_8bpc_neon: 1028.9
mask_w64_8bpc_c: 12735.3
mask_w64_8bpc_neon: 2533.2
mask_w128_8bpc_c: 31027.6
mask_w128_8bpc_neon: 6247.2

Ordering the elements this way is more SIMD-friendly.

Janne Grunau authored Oct 18, 2018 and Ronald S. Bultje committed Oct 20, 2018

The simplified versions catches tg_start != 0 for the first tile group
too. Fixes a heap-buffer-overflow in setup_tile when the first tile index is
larger than 0 but the number of tiles is correct. Fixes #61, #73.

Fixes stack buffer overflows.

Sets the meson b_ndebug option to default to if-release,
so that asserts are disabled in release builds.

Helped-by: Henrik Gramner <gramner@twoorioles.com>

This will help when writing x86_64 assembly.

Martin Storsjö authored Oct 19, 2018 and Marvin Scholz committed Oct 19, 2018

This fixes warnings like these, if not all bitdepths are enabled:

../src/decode.c: In function ‘dav1d_submit_frame’:
../src/decode.c:2825:5: warning: "CONFIG_10BPC" is not defined [-Wundef]
 #if CONFIG_10BPC

Despite what MSDN says, this intrinsic doesn't exist for ARM,
only for ARM64.

All the functions are public, and the only prototype in this header
is a duplicate.

Janne Grunau authored Oct 17, 2018 and Ronald S. Bultje committed Oct 18, 2018

Fix following ubsan error in #68:
../src/env.h:296:24: runtime error: shift exponent -1 is negative
[Detaching after fork from child process 22253]
    #0 0x7ffff76ad6f9 in get_poc_diff /home/janne/src/dav1d/build-usan/../src/env.h:296:24
    #1 0x7ffff76ad6f9 in parse_frame_hdr /home/janne/src/dav1d/build-usan/../src/obu.c:757
    #2 0x7ffff7696491 in dav1d_parse_obus /home/janne/src/dav1d/build-usan/../src/obu.c:1023:20
    #3 0x7ffff7921c7d in dav1d_decode /home/janne/src/dav1d/build-usan/../src/lib.c:193:20
    #4 0x424869 in main /home/janne/src/dav1d/build-usan/../tools/dav1d.c:108:20
    #5 0x7ffff63dfae6 in __libc_start_main (/lib64/libc.so.6+0x21ae6)
    #6 0x403489 in _start (/home/janne/src/dav1d/build-usan/tools/dav1d+0x403489)

I can't reproduce the ubsan error in the issue.

Janne Grunau authored Oct 17, 2018 and Ronald S. Bultje committed Oct 18, 2018

Reject out of range values as errors and avoid undefined shifts. Fixes #67.

Janne Grunau authored Oct 17, 2018 and Ronald S. Bultje committed Oct 18, 2018

Fixes #66. Also fixes a leak of the demuxer context.

Janne Grunau authored Oct 17, 2018 and Ronald S. Bultje committed Oct 18, 2018

Fixes #66.

Janne Grunau authored Oct 17, 2018 and Ronald S. Bultje committed Oct 18, 2018

Fixes #62.

Janne Grunau authored Oct 15, 2018 and Ronald S. Bultje committed Oct 18, 2018

Reverts commit f17c5e08 "check IntraBC
displacement vector".
Fixes #63 and an overlapping memcpy in
clusterfuzz-testcase-minimized-dav1d_fuzzer-5675967192760320. Credits to
oss-fuzz and Tyson Smith.

wiener_luma_8bpc_c: 326272.1
wiener_luma_8bpc_avx2: 19841.5

Decoding time of first 1000 frames of Chimera-8bit-1920x1080.ivf goes
from 27.471 to 23.558 seconds.

Also copy 4 pixels so SIMD can use a padded write (movd).

Deriving uvtx for chroma-from-luma is the same for lossless.
The availability of CfL is constrained to when they match.

Removes the splat of pixels that are then overwritten.
Rename cfl_pred_1 to cfl_pred now that there is only one.

Janne Grunau authored Oct 13, 2018 and Jean-Baptiste Kempf committed Oct 13, 2018

Fixes emmory leak with asan seen with 'dav1d --tilethreads 2 ...'

Janne Grunau authored Oct 11, 2018 and Jean-Baptiste Kempf committed Oct 13, 2018

Makes the tile parsing code simpler. Fixes a heap buffer overflow with
clusterfuzz-testcase-minimized-dav1d_fuzzer-5726018392817664. Credit to
oss-fuzz.

Janne Grunau authored Oct 13, 2018 and Jean-Baptiste Kempf committed Oct 13, 2018

When breaking out of the decoding either through an error or reaching
the limit of decoded frames the input buffer might not be fully consumed
by the previous dav1d_decode() call. Fixes a memory leak discovered
while testing with frame and tile threads with --limit.

Janne Grunau authored Oct 11, 2018 and Jean-Baptiste Kempf committed Oct 13, 2018

Fixes a heap buffer overflow in
clusterfuzz-testcase-minimized-dav1d_fuzzer-5677513716531200. Credits to
oss-fuzz.

On ARM, the readtime implementations are instructions that might
not always be allowed at runtime (depending on whether the kernel
has allowed user mode code to access the cycle counter registers).
In order to allow building checkasm with the option for benchmarking,
while still running on devices where benchmarking isn't possible,
don't use readtime anywhere unless --bench has been specified.

Use GetTickCount for the seed on windows, and gettimeofday on unix.