GitLab

Fixes #183. Fixes use of uninitialized data in apply_to_row_uv with odd
width in clusterfuzz-testcase-minimized-dav1d_fuzzer-5684823666982912.
Credits to oss-fuzz.

Fixed 00000802.ivf.

Martin Storsjö authored Nov 05, 2018 and Janne Grunau committed Nov 21, 2018

This avoids a misoptimization in clang,
https://bugs.llvm.org/show_bug.cgi?id=39550, where the root cause
has been around for a number of years, but a change in LLVM 6.0
allowed for better optimizations, exposing this bug. This bug is
on good track to be fixed in LLVM for the 8.0 release and hopefully
also for backporting into 7.0.1. It is however present in 6.0, 6.0.1
and 7.0, and other downstream users such as Xcode 10.0/10.1.

Ronald S. Bultje authored Nov 21, 2018 and Jean-Baptiste Kempf committed Nov 21, 2018

Fixes 00000527.ivf in #186.

Also ensure we apply film-grain to delayed pictures.

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

Fixes clusterfuzz-testcase-minimized-dav1d_fuzzer-5730334348410880,
with credits to oss-fuzz.

Fixes an undefined left shift of a negative value in
clusterfuzz-testcase-minimized-dav1d_fuzzer-5707215277654016. Credits to
oss-fuzz.

This does not adjust the AVX2 asm. The asm clips in many places to the
required range (16-bit signed) for performance reason. No mismatch
observed with coefs generated by the forward transform in checkasm in
10 thousand runs.

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

These edges don't encode LR coefficients anyway. Fixes
clusterfuzz-testcase-minimized-dav1d_fuzzer-5731769337249792.
Credits to oss-fuzz.

Martin Storsjö authored Nov 20, 2018 and Jean-Baptiste Kempf committed Nov 20, 2018

This fixes compiler errors like these:
src/film_grain_tmpl.c(238): error C2036: 'void *': unknown size

Don't rely on sizeof(void) == 1 in pointer arithmetic, but instead
cast the row pointers to the pixel datatype immediately, use PXSTRIDE()
for converting a stride in byte units to pixel units, and skip
sizeof(pixel) for horizontal offsets that previously were applied on
a void pointer.

Fixes a deadlock on teardown with
clusterfuzz-testcase-minimized-dav1d_fuzzer_mt-5636065151418368. Credits
to oss-fuzz.

Fixes warnings about redefinition of _WIN32_WINNT on Windows targets

Niklas Haas authored Nov 13, 2018 and Ronald S. Bultje committed Nov 19, 2018

This is using a slightly adapted version of my GPU-based algorithm. The
major difference to the algorithm suggested by the spec (and implemented
in libaom) is that instead of using a line buffer to hold the previous
row's film grain blocks, we compute each row/block fully independently.

This opens up the door to exploit parallelism in the future, since we
don't have any left->right or top->down dependency except for the PRNG
state. (Which we could pre-compute for a massively parallel / GPU
implementation)

That being said, it's probably somewhat slower than using a line buffer
for the serial / single CPU case, although most likely not by much
(since the areas with the most redundant work get progressively smaller,
down to a single 2x2 square for the worst case).

Niklas Haas authored Nov 13, 2018 and Ronald S. Bultje committed Nov 19, 2018

This becomes part of the picture properties, since users may want to
apply film grain themselves (e.g. for a GPU implementation).

Niklas Haas authored Oct 28, 2018 and Ronald S. Bultje committed Nov 19, 2018

The spec subtracts the signed offset from all of these when using them,
like it does for e.g. ar_coeffs_y_plus_128, although for some reason
the naming scheme is inconsistent here. Either way, it makes more sense
to treat them as signed integers than unsigned integers.

To avoid confusion since the name of the field is the same as the one in
the spec, we mark the type as int8_t (resp. int16_t for the 9-bit field)
to make it clear to the user that these are already signed integers.

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

Fixes #183.

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

Also fix a calculation for u_idx. Fixes 5646860283281408 of #183.

Martin Storsjö authored Oct 27, 2018 and Janne Grunau committed Nov 18, 2018

These functions have been tuned against Cortex A53 and Snapdragon
835. The bilin functions have mainly been written with code size
in mind, as they aren't used much in practice.

Relative speedups for the actual filtering fuctions (that don't
just do a plain copy) are around 4-15x, some over 20x. This is
in comparison with GCC 5.4 with autovectorization disabled; the
actual real-world speedup against autovectorized C code is around
4-10x.

Relative speedups measured with checkasm:
                                Cortex A53   Snapdragon 835
mc_8tap_regular_w2_0_8bpc_neon:       6.96   5.28
mc_8tap_regular_w2_h_8bpc_neon:       5.16   4.35
mc_8tap_regular_w2_hv_8bpc_neon:      5.37   4.98
mc_8tap_regular_w2_v_8bpc_neon:       6.35   4.85
mc_8tap_regular_w4_0_8bpc_neon:       6.78   5.73
mc_8tap_regular_w4_h_8bpc_neon:       8.40   6.60
mc_8tap_regular_w4_hv_8bpc_neon:      7.23   7.10
mc_8tap_regular_w4_v_8bpc_neon:       9.06   7.76
mc_8tap_regular_w8_0_8bpc_neon:       6.96   5.55
mc_8tap_regular_w8_h_8bpc_neon:      10.36   6.88
mc_8tap_regular_w8_hv_8bpc_neon:      9.49   6.86
mc_8tap_regular_w8_v_8bpc_neon:      12.06   9.61
mc_8tap_regular_w16_0_8bpc_neon:      6.68   4.51
mc_8tap_regular_w16_h_8bpc_neon:     12.30   7.77
mc_8tap_regular_w16_hv_8bpc_neon:     9.50   6.68
mc_8tap_regular_w16_v_8bpc_neon:     12.93   9.68
mc_8tap_regular_w32_0_8bpc_neon:      3.91   2.93
mc_8tap_regular_w32_h_8bpc_neon:     13.06   7.89
mc_8tap_regular_w32_hv_8bpc_neon:     9.37   6.70
mc_8tap_regular_w32_v_8bpc_neon:     12.88   9.49
mc_8tap_regular_w64_0_8bpc_neon:      2.89   1.68
mc_8tap_regular_w64_h_8bpc_neon:     13.48   8.00
mc_8tap_regular_w64_hv_8bpc_neon:     9.23   6.53
mc_8tap_regular_w64_v_8bpc_neon:     13.11   9.68
mc_8tap_regular_w128_0_8bpc_neon:     1.89   1.24
mc_8tap_regular_w128_h_8bpc_neon:    13.58   7.98
mc_8tap_regular_w128_hv_8bpc_neon:    8.86   6.53
mc_8tap_regular_w128_v_8bpc_neon:    12.46   9.63
mc_bilinear_w2_0_8bpc_neon:           7.02   5.40
mc_bilinear_w2_h_8bpc_neon:           3.65   3.14
mc_bilinear_w2_hv_8bpc_neon:          4.36   4.84
mc_bilinear_w2_v_8bpc_neon:           5.22   4.28
mc_bilinear_w4_0_8bpc_neon:           6.87   5.99
mc_bilinear_w4_h_8bpc_neon:           6.50   8.61
mc_bilinear_w4_hv_8bpc_neon:          7.70   7.99
mc_bilinear_w4_v_8bpc_neon:           7.04   9.10
mc_bilinear_w8_0_8bpc_neon:           7.03   5.70
mc_bilinear_w8_h_8bpc_neon:          11.30  15.14
mc_bilinear_w8_hv_8bpc_neon:         15.74  13.50
mc_bilinear_w8_v_8bpc_neon:          13.40  17.54
mc_bilinear_w16_0_8bpc_neon:          6.75   4.48
mc_bilinear_w16_h_8bpc_neon:         17.02  13.95
mc_bilinear_w16_hv_8bpc_neon:        17.37  13.78
mc_bilinear_w16_v_8bpc_neon:         23.69  22.98
mc_bilinear_w32_0_8bpc_neon:          3.88   3.18
mc_bilinear_w32_h_8bpc_neon:         18.80  14.97
mc_bilinear_w32_hv_8bpc_neon:        17.74  14.02
mc_bilinear_w32_v_8bpc_neon:         24.46  23.04
mc_bilinear_w64_0_8bpc_neon:          2.87   1.66
mc_bilinear_w64_h_8bpc_neon:         19.54  16.02
mc_bilinear_w64_hv_8bpc_neon:        17.80  14.32
mc_bilinear_w64_v_8bpc_neon:         24.79  23.63
mc_bilinear_w128_0_8bpc_neon:         2.13   1.23
mc_bilinear_w128_h_8bpc_neon:        19.89  16.24
mc_bilinear_w128_hv_8bpc_neon:       17.55  14.15
mc_bilinear_w128_v_8bpc_neon:        24.45  23.54
mct_8tap_regular_w4_0_8bpc_neon:      5.56   5.51
mct_8tap_regular_w4_h_8bpc_neon:      7.48   5.80
mct_8tap_regular_w4_hv_8bpc_neon:     7.27   7.09
mct_8tap_regular_w4_v_8bpc_neon:      7.80   6.84
mct_8tap_regular_w8_0_8bpc_neon:      9.54   9.25
mct_8tap_regular_w8_h_8bpc_neon:      9.08   6.55
mct_8tap_regular_w8_hv_8bpc_neon:     9.16   6.30
mct_8tap_regular_w8_v_8bpc_neon:     10.79   8.66
mct_8tap_regular_w16_0_8bpc_neon:    15.35  10.50
mct_8tap_regular_w16_h_8bpc_neon:    10.18   6.76
mct_8tap_regular_w16_hv_8bpc_neon:    9.17   6.11
mct_8tap_regular_w16_v_8bpc_neon:    11.52   8.72
mct_8tap_regular_w32_0_8bpc_neon:    15.82  10.09
mct_8tap_regular_w32_h_8bpc_neon:    10.75   6.85
mct_8tap_regular_w32_hv_8bpc_neon:    9.00   6.22
mct_8tap_regular_w32_v_8bpc_neon:    11.58   8.67
mct_8tap_regular_w64_0_8bpc_neon:    15.28   9.68
mct_8tap_regular_w64_h_8bpc_neon:    10.93   6.96
mct_8tap_regular_w64_hv_8bpc_neon:    8.81   6.53
mct_8tap_regular_w64_v_8bpc_neon:    11.42   8.73
mct_8tap_regular_w128_0_8bpc_neon:   14.41   7.67
mct_8tap_regular_w128_h_8bpc_neon:   10.92   6.96
mct_8tap_regular_w128_hv_8bpc_neon:   8.56   6.51
mct_8tap_regular_w128_v_8bpc_neon:   11.16   8.70
mct_bilinear_w4_0_8bpc_neon:          5.66   5.77
mct_bilinear_w4_h_8bpc_neon:          5.16   6.40
mct_bilinear_w4_hv_8bpc_neon:         6.86   6.82
mct_bilinear_w4_v_8bpc_neon:          4.75   6.09
mct_bilinear_w8_0_8bpc_neon:          9.78  10.00
mct_bilinear_w8_h_8bpc_neon:          8.98  11.37
mct_bilinear_w8_hv_8bpc_neon:        14.42  10.83
mct_bilinear_w8_v_8bpc_neon:          9.12  11.62
mct_bilinear_w16_0_8bpc_neon:        15.59  10.76
mct_bilinear_w16_h_8bpc_neon:        11.98   8.77
mct_bilinear_w16_hv_8bpc_neon:       15.83  10.73
mct_bilinear_w16_v_8bpc_neon:        14.70  14.60
mct_bilinear_w32_0_8bpc_neon:        15.89  10.32
mct_bilinear_w32_h_8bpc_neon:        13.47   9.07
mct_bilinear_w32_hv_8bpc_neon:       16.01  10.95
mct_bilinear_w32_v_8bpc_neon:        14.85  14.16
mct_bilinear_w64_0_8bpc_neon:        15.36  10.51
mct_bilinear_w64_h_8bpc_neon:        14.00   9.61
mct_bilinear_w64_hv_8bpc_neon:       15.82  11.27
mct_bilinear_w64_v_8bpc_neon:        14.61  14.76
mct_bilinear_w128_0_8bpc_neon:       14.41   7.92
mct_bilinear_w128_h_8bpc_neon:       13.31   9.58
mct_bilinear_w128_hv_8bpc_neon:      14.07  11.18
mct_bilinear_w128_v_8bpc_neon:       11.57  14.42

Fixes #149.

This reverts commit 597a6eb9. It leads to
assertion failures in oss-fuzz.

Fixes unaligned writes while splatting coefs for skip blocks with
clusterfuzz-testcase-minimized-dav1d_fuzzer_mt-5684725352497152 and
clusterfuzz-testcase-minimized-dav1d_fuzzer_mt-5728508249112576.

Ronald S. Bultje authored Nov 16, 2018 and Janne Grunau committed Nov 16, 2018

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.

This is consistent with what libaom does. Should fix #175.

Fixes #172.

The race is exposed by not draining the decoder correctly after
02606969 (decoupled decoding api). Fixes a memleak with
clusterfuzz-testcase-minimized-dav1d_fuzzer_mt-5728508249112576. Credits
to oss-fuzz.

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

But don't abort decoding; instead, simply force translational motion.

boyuanxiao-argondesign authored Nov 09, 2018 and Ronald S. Bultje committed Nov 15, 2018

See section 7.11.2.4 in AV1 spec. Because frame contexts are not
passed into the ipred_z*_c functions the flag is set as a bit inside
the 'angle' function argument.

boyuanxiao-argondesign authored Nov 13, 2018 and Ronald S. Bultje committed Nov 15, 2018

A new coded video sequence (see page 193; section 7.5 of the spec)
begins when we see a sequence header that isn't bit identical to
previous ones. This is the point at which we can throw away previous
frames etc.