OSDN Git Service
Diego Biurrun [Tue, 15 Nov 2016 15:17:05 +0000 (16:17 +0100)]
qsv: Drop some unused variables
Diego Biurrun [Tue, 8 Dec 2015 15:54:07 +0000 (16:54 +0100)]
examples/transcode_aac: Drop pointless return value const qualifier
doc/examples/transcode_aac.c:52:20: warning: type qualifiers ignored on function return type [-Wignored-qualifiers]
Diego Biurrun [Wed, 16 Nov 2016 09:34:38 +0000 (09:34 +0000)]
Ignore all generated example binaries
Stephen Hutchinson [Sat, 29 Oct 2016 00:52:11 +0000 (20:52 -0400)]
doc: Add note about recent regression in AviSynth+
Signed-off-by: Diego Biurrun <diego@biurrun.de>
Stephen Hutchinson [Thu, 27 Oct 2016 02:54:18 +0000 (22:54 -0400)]
avisynth: Support pix_fmts added to AviSynth+
A number of new pix_fmts* have been added to AviSynth+:
16-bit packed RGB and RGBA
10-, 12-, 14, and 16-bit YUV 4:2:0, 4:2:2, and 4:4:4
8-, 10-, 12-, 14-, and 16-bit Planar RGB
8-, 10-, 12-, 14-, and 16-bit Planar YUVA and Planar RGBA
10-, 12-, 14-, and 16-bit GRAY variants
32-bit floating point Planar YUV(A), Planar RGB(A), and GRAY
*some of which are not currently available pix_fmts here and were
not added to the demuxer due to this
Signed-off-by: Diego Biurrun <diego@biurrun.de>
Stephen Hutchinson [Mon, 8 Aug 2016 23:24:19 +0000 (19:24 -0400)]
avisynth: Simplify the pix_fmt check for the newer AviSynth API
The values don't need to be hardcoded since the correct values are
returned by avs_bits_per_pixel.
Signed-off-by: Diego Biurrun <diego@biurrun.de>
Marton Balint [Mon, 8 Aug 2016 23:24:18 +0000 (19:24 -0400)]
avisynth: Fix setting stream timebase
Stream timebase should be set using avpriv_set_pts_info, otherwise
avctx->pkt_timebase is not correct, leading to A/V desync.
Signed-off-by: Marton Balint <cus@passwd.hu>
Reviewed-by: Stephen Hutchinson <qyot27@gmail.com>
Signed-off-by: Diego Biurrun <diego@biurrun.de>
Vittorio Giovara [Tue, 8 Nov 2016 21:47:38 +0000 (16:47 -0500)]
fate: Add h264 and hevc extradata reload tests
Signed-off-by: Vittorio Giovara <vittorio.giovara@gmail.com>
Vittorio Giovara [Tue, 15 Nov 2016 15:14:30 +0000 (10:14 -0500)]
mov: Fix identity matrix boolean logic
This prevented the code from correctly exporting the rotation matrix
which caused a few samples to be displayed wrong.
Introduced in
ecd2ec69ce10e13f6ede353d2def7c.
Signed-off-by: Vittorio Giovara <vittorio.giovara@gmail.com>
Martin Storsjö [Mon, 14 Nov 2016 21:44:06 +0000 (23:44 +0200)]
checkasm: vp9dsp: Benchmark the dc-only version of idct_idct separately
The dc-only mode is already checked to work correctly above, but this
allows benchmarking this mode for performance tuning, and allows making
sure that it actually is correctly hooked up.
Signed-off-by: Martin Storsjö <martin@martin.st>
Janne Grunau [Mon, 14 Nov 2016 21:35:13 +0000 (22:35 +0100)]
aarch64: vp9: loop filter: replace 'orr; cbn?z' with 'adds; b.{eq,ne};
The latter is 1 cycle faster on a cortex-53 and since the operands are
bytewise (or larger) bitmask (impossible to overflow to zero) both are
equivalent.
Janne Grunau [Sun, 13 Nov 2016 23:13:34 +0000 (00:13 +0100)]
aarch64: vp9: use alternative returns in the core loop filter function
Since aarch64 has enough free general purpose registers use them to
branch to the appropiate storage code. 1-2 cycles faster for the
functions using loop_filter 8/16, ... on a cortex-a53. Mixed results
(up to 2 cycles faster/slower) on a cortex-a57.
Gianluigi Tiesi [Fri, 19 Sep 2014 02:49:36 +0000 (04:49 +0200)]
libilbc: support for latest git of libilbc
In the latest git commits of libilbc developers removed WebRtc_xxx typedefs.
This commit uses int types instead. It's safe to apply also for previous
versions since WebRtc_Word16 was always a typedef of int16_t and
WebRtc_UWord16 a typedef of uint16_t.
Reviewed-by: Timothy Gu <timothygu99@gmail.com>
Signed-off-by: Diego Biurrun <diego@biurrun.de>
Diego Biurrun [Thu, 10 Nov 2016 16:11:42 +0000 (17:11 +0100)]
configure: Move mjpeg_vaapi_decoder dependency declarations to the right place
Diego Biurrun [Fri, 11 Dec 2015 16:37:01 +0000 (17:37 +0100)]
golomb: Replace __PRETTY_FUNCTION__ with __func__ for tracing
The former is a GNU extension while the latter is C99.
Diego Biurrun [Mon, 4 Jan 2016 10:14:51 +0000 (11:14 +0100)]
af_asyncts: Use llabs instead of labs for 64-bit variable
libavfilter/af_asyncts.c:212:9: warning: absolute value function 'labs' given an argument of type 'int64_t' (aka 'long long') but has parameter of type 'long' which may cause truncation of value [-Wabsolute-value]
Mark Thompson [Thu, 27 Oct 2016 19:33:56 +0000 (20:33 +0100)]
qsv: Add VP8 decoder
Mark Thompson [Thu, 27 Oct 2016 19:02:29 +0000 (20:02 +0100)]
vp8: Return stream format information from parser
Mark Thompson [Wed, 26 Oct 2016 20:29:08 +0000 (21:29 +0100)]
qsv: Add VC-1 decoder
It uses the same code as the MPEG-2 decoder, so the file is renamed
to contain all "other" (that is, not H.26[45]) codecs.
Mark Thompson [Wed, 26 Oct 2016 20:13:45 +0000 (21:13 +0100)]
vc1: Return stream format information from parser
Mark Thompson [Sun, 30 Oct 2016 16:58:23 +0000 (16:58 +0000)]
qsvdec: Only warn about unconsumed data if it happens more than once
Mark Thompson [Wed, 26 Oct 2016 20:27:49 +0000 (21:27 +0100)]
qsvdec: Pass field order information to libmfx
The VC-1 decoder fails to initialise if this is not set.
Mark Thompson [Wed, 26 Oct 2016 20:26:10 +0000 (21:26 +0100)]
qsvdec: Pass the correct profile to libmfx
This was correct for H.26[45], because libmfx uses the same values
derived from profile_idc and the constraint_set flags, but it is
wrong for other codecs.
Also avoid passing FF_LEVEL_UNKNOWN (-99) as the level, as this is
certainly invalid.
Mark Thompson [Wed, 26 Oct 2016 20:12:02 +0000 (21:12 +0100)]
mpegvideo: Return correct coded frame sizes from parser
Janne Grunau [Mon, 14 Nov 2016 00:16:00 +0000 (01:16 +0100)]
aarch64: vp9: loop_filter: fix typo in skip flatout8 check
The 16_16 loop filter functions could miss an early exit before
flatout8.
Signed-off-by: Martin Storsjö <martin@martin.st>
Martin Storsjö [Sun, 13 Nov 2016 22:07:27 +0000 (00:07 +0200)]
aarch64: vp9: Implement NEON loop filters
This work is sponsored by, and copyright, Google.
These are ported from the ARM version; thanks to the larger
amount of registers available, we can do the loop filters with
16 pixels at a time. The implementation is fully templated, with
a single macro which can generate versions for both 8 and
16 pixels wide, for both 4, 8 and 16 pixels loop filters
(and the 4/8 mixed versions as well).
For the 8 pixel wide versions, it is pretty close in speed (the
v_4_8 and v_8_8 filters are the best examples of this; the h_4_8
and h_8_8 filters seem to get some gain in the load/transpose/store
part). For the 16 pixels wide ones, we get a speedup of around
1.2-1.4x compared to the 32 bit version.
Examples of runtimes vs the 32 bit version, on a Cortex A53:
ARM AArch64
vp9_loop_filter_h_4_8_neon: 144.0 127.2
vp9_loop_filter_h_8_8_neon: 207.0 182.5
vp9_loop_filter_h_16_8_neon: 415.0 328.7
vp9_loop_filter_h_16_16_neon: 672.0 558.6
vp9_loop_filter_mix2_h_44_16_neon: 302.0 203.5
vp9_loop_filter_mix2_h_48_16_neon: 365.0 305.2
vp9_loop_filter_mix2_h_84_16_neon: 365.0 305.2
vp9_loop_filter_mix2_h_88_16_neon: 376.0 305.2
vp9_loop_filter_mix2_v_44_16_neon: 193.2 128.2
vp9_loop_filter_mix2_v_48_16_neon: 246.7 218.4
vp9_loop_filter_mix2_v_84_16_neon: 248.0 218.5
vp9_loop_filter_mix2_v_88_16_neon: 302.0 218.2
vp9_loop_filter_v_4_8_neon: 89.0 88.7
vp9_loop_filter_v_8_8_neon: 141.0 137.7
vp9_loop_filter_v_16_8_neon: 295.0 272.7
vp9_loop_filter_v_16_16_neon: 546.0 453.7
The speedup vs C code in checkasm tests is around 2-7x, which is
pretty much the same as for the 32 bit version. Even if these functions
are faster than their 32 bit equivalent, the C version that we compare
to also became around 1.3-1.7x faster than the C version in 32 bit.
Based on START_TIMER/STOP_TIMER wrapping around a few individual
functions, the speedup vs C code is around 4-5x.
Examples of runtimes vs C on a Cortex A57 (for a slightly older version
of the patch):
A57 gcc-5.3 neon
loop_filter_h_4_8_neon: 256.6 93.4
loop_filter_h_8_8_neon: 307.3 139.1
loop_filter_h_16_8_neon: 340.1 254.1
loop_filter_h_16_16_neon: 827.0 407.9
loop_filter_mix2_h_44_16_neon: 524.5 155.4
loop_filter_mix2_h_48_16_neon: 644.5 173.3
loop_filter_mix2_h_84_16_neon: 630.5 222.0
loop_filter_mix2_h_88_16_neon: 697.3 222.0
loop_filter_mix2_v_44_16_neon: 598.5 100.6
loop_filter_mix2_v_48_16_neon: 651.5 127.0
loop_filter_mix2_v_84_16_neon: 591.5 167.1
loop_filter_mix2_v_88_16_neon: 855.1 166.7
loop_filter_v_4_8_neon: 271.7 65.3
loop_filter_v_8_8_neon: 312.5 106.9
loop_filter_v_16_8_neon: 473.3 206.5
loop_filter_v_16_16_neon: 976.1 327.8
The speed-up compared to the C functions is 2.5 to 6 and the cortex-a57
is again 30-50% faster than the cortex-a53.
Signed-off-by: Martin Storsjö <martin@martin.st>
Martin Storsjö [Sat, 12 Nov 2016 19:25:50 +0000 (21:25 +0200)]
arm: vp9itxfm: Simplify txfm string comparisons
Signed-off-by: Martin Storsjö <martin@martin.st>
Martin Storsjö [Sun, 13 Nov 2016 21:53:08 +0000 (23:53 +0200)]
aarch64: vp9: Add NEON itxfm routines
This work is sponsored by, and copyright, Google.
These are ported from the ARM version; thanks to the larger
amount of registers available, we can do the 16x16 and 32x32
transforms in slices 8 pixels wide instead of 4. This gives
a speedup of around 1.4x compared to the 32 bit version.
The fact that aarch64 doesn't have the same d/q register
aliasing makes some of the macros quite a bit simpler as well.
Examples of runtimes vs the 32 bit version, on a Cortex A53:
ARM AArch64
vp9_inv_adst_adst_4x4_add_neon: 90.0 87.7
vp9_inv_adst_adst_8x8_add_neon: 400.0 354.7
vp9_inv_adst_adst_16x16_add_neon: 2526.5 1827.2
vp9_inv_dct_dct_4x4_add_neon: 74.0 72.7
vp9_inv_dct_dct_8x8_add_neon: 271.0 256.7
vp9_inv_dct_dct_16x16_add_neon: 1960.7 1372.7
vp9_inv_dct_dct_32x32_add_neon: 11988.9 8088.3
vp9_inv_wht_wht_4x4_add_neon: 63.0 57.7
The speedup vs C code (2-4x) is smaller than in the 32 bit case,
mostly because the C code ends up significantly faster (around
1.6x faster, with GCC 5.4) when built for aarch64.
Examples of runtimes vs C on a Cortex A57 (for a slightly older version
of the patch):
A57 gcc-5.3 neon
vp9_inv_adst_adst_4x4_add_neon: 152.2 60.0
vp9_inv_adst_adst_8x8_add_neon: 948.2 288.0
vp9_inv_adst_adst_16x16_add_neon: 4830.4 1380.5
vp9_inv_dct_dct_4x4_add_neon: 153.0 58.6
vp9_inv_dct_dct_8x8_add_neon: 789.2 180.2
vp9_inv_dct_dct_16x16_add_neon: 3639.6 917.1
vp9_inv_dct_dct_32x32_add_neon: 20462.1 4985.0
vp9_inv_wht_wht_4x4_add_neon: 91.0 49.8
The asm is around factor 3-4 faster than C on the cortex-a57 and the asm
is around 30-50% faster on the a57 compared to the a53.
Signed-off-by: Martin Storsjö <martin@martin.st>
Diego Biurrun [Sun, 6 Dec 2015 12:04:05 +0000 (13:04 +0100)]
avconv_opt: Consistently iterate through hwaccels array in all cases
avconv_opt.c:188:19: warning: comparison of unsigned expression < 0 is always false [-Wtype-limits]
Diego Biurrun [Fri, 30 Oct 2015 14:26:25 +0000 (15:26 +0100)]
Drop pointless void* casts
Diego Biurrun [Sun, 15 Mar 2015 14:56:52 +0000 (15:56 +0100)]
aac: Drop pointless cast
Diego Biurrun [Fri, 30 Oct 2015 14:21:19 +0000 (15:21 +0100)]
vf_drawtext: Drop wrong void* cast
libavfilter/vf_drawtext.c:844:49: warning: ISO C forbids conversion of function pointer to object pointer type [-Wpedantic]
Diego Biurrun [Fri, 30 Oct 2015 14:27:56 +0000 (15:27 +0100)]
nut: Use correct function pointer casts instead of void*
Fixes several warnings of the type
libavformat/nut.c:207:42: warning: ISO C forbids conversion of function pointer to object pointer type [-Wpedantic]
Diego Biurrun [Thu, 12 Mar 2015 23:36:41 +0000 (00:36 +0100)]
ratecontrol: Use correct function pointer casts instead of void*
libavcodec/ratecontrol.c:120:9: warning: ISO C forbids initialization between function pointer and ‘void *’ [-Wpedantic]
libavcodec/ratecontrol.c:121:9: warning: ISO C forbids initialization between function pointer and ‘void *’ [-Wpedantic]
Martin Storsjö [Mon, 10 Oct 2016 06:48:03 +0000 (09:48 +0300)]
arm: vp9: Add NEON loop filters
This work is sponsored by, and copyright, Google.
The implementation tries to have smart handling of cases
where no pixels need the full filtering for the 8/16 width
filters, skipping both calculation and writeback of the
unmodified pixels in those cases. The actual effect of this
is hard to test with checkasm though, since it tests the
full filtering, and the benefit depends on how many filtered
blocks use the shortcut.
Examples of relative speedup compared to the C version, from checkasm:
Cortex A7 A8 A9 A53
vp9_loop_filter_h_4_8_neon: 2.72 2.68 1.78 3.15
vp9_loop_filter_h_8_8_neon: 2.36 2.38 1.70 2.91
vp9_loop_filter_h_16_8_neon: 1.80 1.89 1.45 2.01
vp9_loop_filter_h_16_16_neon: 2.81 2.78 2.18 3.16
vp9_loop_filter_mix2_h_44_16_neon: 2.65 2.67 1.93 3.05
vp9_loop_filter_mix2_h_48_16_neon: 2.46 2.38 1.81 2.85
vp9_loop_filter_mix2_h_84_16_neon: 2.50 2.41 1.73 2.85
vp9_loop_filter_mix2_h_88_16_neon: 2.77 2.66 1.96 3.23
vp9_loop_filter_mix2_v_44_16_neon: 4.28 4.46 3.22 5.70
vp9_loop_filter_mix2_v_48_16_neon: 3.92 4.00 3.03 5.19
vp9_loop_filter_mix2_v_84_16_neon: 3.97 4.31 2.98 5.33
vp9_loop_filter_mix2_v_88_16_neon: 3.91 4.19 3.06 5.18
vp9_loop_filter_v_4_8_neon: 4.53 4.47 3.31 6.05
vp9_loop_filter_v_8_8_neon: 3.58 3.99 2.92 5.17
vp9_loop_filter_v_16_8_neon: 3.40 3.50 2.81 4.68
vp9_loop_filter_v_16_16_neon: 4.66 4.41 3.74 6.02
The speedup vs C code is around 2-6x. The numbers are quite
inconclusive though, since the checkasm test runs multiple filterings
on top of each other, so later rounds might end up with different
codepaths (different decisions on which filter to apply, based
on input pixel differences). Disabling the early-exit in the asm
doesn't give a fair comparison either though, since the C code
only does the necessary calcuations for each row.
Based on START_TIMER/STOP_TIMER wrapping around a few individual
functions, the speedup vs C code is around 4-9x.
This is pretty similar in runtime to the corresponding routines
in libvpx. (This is comparing vpx_lpf_vertical_16_neon,
vpx_lpf_horizontal_edge_8_neon and vpx_lpf_horizontal_edge_16_neon
to vp9_loop_filter_h_16_8_neon, vp9_loop_filter_v_16_8_neon
and vp9_loop_filter_v_16_16_neon - note that the naming of horizonal
and vertical is flipped between the libraries.)
In order to have stable, comparable numbers, the early exits in both
asm versions were disabled, forcing the full filtering codepath.
Cortex A7 A8 A9 A53
vp9_loop_filter_h_16_8_neon: 597.2 472.0 482.4 415.0
libvpx vpx_lpf_vertical_16_neon: 626.0 464.5 470.7 445.0
vp9_loop_filter_v_16_8_neon: 500.2 422.5 429.7 295.0
libvpx vpx_lpf_horizontal_edge_8_neon: 586.5 414.5 415.6 383.2
vp9_loop_filter_v_16_16_neon: 905.0 784.7 791.5 546.0
libvpx vpx_lpf_horizontal_edge_16_neon: 1060.2 751.7 743.5 685.2
Our version is consistently faster on on A7 and A53, marginally slower on
A8, and sometimes faster, sometimes slower on A9 (marginally slower in all
three tests in this particular test run).
Signed-off-by: Martin Storsjö <martin@martin.st>
Diego Biurrun [Tue, 8 Dec 2015 09:22:15 +0000 (10:22 +0100)]
libxvid: Check return value of write() call
libavcodec/libxvid_rc.c:106:9: warning: ignoring return value of ‘write’, declared with attribute warn_unused_result [-Wunused-result]
Diego Biurrun [Tue, 8 Dec 2015 09:21:27 +0000 (10:21 +0100)]
libxvid: Use proper context in av_log() calls
Diego Biurrun [Thu, 12 Feb 2015 09:11:22 +0000 (10:11 +0100)]
libxvid: Require availability of mkstemp()
The replacement code uses tempnam(), which is dangerous.
Such a fringe feature is not worth the trouble.
Martin Storsjö [Sat, 8 Oct 2016 19:36:18 +0000 (22:36 +0300)]
arm: vp9: Add NEON itxfm routines
This work is sponsored by, and copyright, Google.
For the transforms up to 8x8, we can fit all the data (including
temporaries) in registers and just do a straightforward transform
of all the data. For 16x16, we do a transform of 4x16 pixels in
4 slices, using a temporary buffer. For 32x32, we transform 4x32
pixels at a time, in two steps of 4x16 pixels each.
Examples of relative speedup compared to the C version, from checkasm:
Cortex A7 A8 A9 A53
vp9_inv_adst_adst_4x4_add_neon: 3.39 5.83 4.17 4.01
vp9_inv_adst_adst_8x8_add_neon: 3.79 4.86 4.23 3.98
vp9_inv_adst_adst_16x16_add_neon: 3.33 4.36 4.11 4.16
vp9_inv_dct_dct_4x4_add_neon: 4.06 6.16 4.59 4.46
vp9_inv_dct_dct_8x8_add_neon: 4.61 6.01 4.98 4.86
vp9_inv_dct_dct_16x16_add_neon: 3.35 3.44 3.36 3.79
vp9_inv_dct_dct_32x32_add_neon: 3.89 3.50 3.79 4.42
vp9_inv_wht_wht_4x4_add_neon: 3.22 5.13 3.53 3.77
Thus, the speedup vs C code is around 3-6x.
This is mostly marginally faster than the corresponding routines
in libvpx on most cores, tested with their 32x32 idct (compared to
vpx_idct32x32_1024_add_neon). These numbers are slightly in libvpx's
favour since their version doesn't clear the input buffer like ours
do (although the effect of that on the total runtime probably is
negligible.)
Cortex A7 A8 A9 A53
vp9_inv_dct_dct_32x32_add_neon: 18436.8 16874.1 14235.1 11988.9
libvpx vpx_idct32x32_1024_add_neon 20789.0 13344.3 15049.9 13030.5
Only on the Cortex A8, the libvpx function is faster. On the other cores,
ours is slightly faster even though ours has got source block clearing
integrated.
Signed-off-by: Martin Storsjö <martin@martin.st>
Ronald S. Bultje [Tue, 22 Sep 2015 18:24:27 +0000 (14:24 -0400)]
checkasm: add vp9dsp.itxfm_add tests.
This includes fixes by Henrik Gramner.
The forward transforms are derived from the reference encoder.
Signed-off-by: Martin Storsjö <martin@martin.st>
Mark Thompson [Thu, 3 Nov 2016 00:13:35 +0000 (00:13 +0000)]
pthread_frame: Unreference hw_frames_ctx on per-thread codec contexts
When decoding with threads enabled, the get_format callback will be
called with one of the per-thread codec contexts rather than with the
outer context. If a hwaccel is in use too, this will add a reference
to the hardware frames context on that codec context, which will then
propagate to all of the other per-thread contexts for decoding. Once
the decoder finishes, however, the per-thread contexts are not freed
normally, so these references leak.
Martin Storsjö [Thu, 10 Nov 2016 11:25:36 +0000 (13:25 +0200)]
arm: vp9mc: Use a different helper register for PIC loads
This fixes crashes since
557c1675cf in linux PIC builds.
Previously, movrelx silently used r12 as helper register, which
doesn't work when r12 is the destination register.
Signed-off-by: Martin Storsjö <martin@martin.st>
Martin Storsjö [Thu, 10 Nov 2016 11:23:38 +0000 (13:23 +0200)]
arm: Clear the gp register alias at the end of functions
We reset .Lpic_gp to zero at the start of each function, which means
that the logic within movrelx for clearing gp when necessary will
be missed.
This fixes using movrelx in different functions with a different
helper register.
Signed-off-by: Martin Storsjö <martin@martin.st>
Diego Biurrun [Wed, 9 Nov 2016 05:07:06 +0000 (06:07 +0100)]
examples/decode_audio: Add missing header for av_free()
Martin Storsjö [Wed, 9 Nov 2016 09:54:25 +0000 (11:54 +0200)]
aarch64: h264idct: Use the offset parameter to movrel
Signed-off-by: Martin Storsjö <martin@martin.st>
Martin Storsjö [Thu, 10 Nov 2016 09:07:39 +0000 (11:07 +0200)]
arm: vp9mc: Minor adjustments from review of the aarch64 version
This work is sponsored by, and copyright, Google.
The speedup for the large horizontal filters is surprisingly
big on A7 and A53, while there's a minor slowdown (almost within
measurement noise) on A8 and A9.
Cortex A7 A8 A9 A53
orig:
vp9_put_8tap_smooth_64h_neon: 20270.0 14447.3 19723.9 10910.9
new:
vp9_put_8tap_smooth_64h_neon: 20165.8 14466.5 19730.2 10668.8
Signed-off-by: Martin Storsjö <martin@martin.st>
Martin Storsjö [Thu, 10 Nov 2016 09:06:26 +0000 (11:06 +0200)]
aarch64: vp9: Add NEON optimizations of VP9 MC functions
This work is sponsored by, and copyright, Google.
These are ported from the ARM version; it is essentially a 1:1
port with no extra added features, but with some hand tuning
(especially for the plain copy/avg functions). The ARM version
isn't very register starved to begin with, so there's not much
to be gained from having more spare registers here - we only
avoid having to clobber callee-saved registers.
Examples of runtimes vs the 32 bit version, on a Cortex A53:
ARM AArch64
vp9_avg4_neon: 27.2 23.7
vp9_avg8_neon: 56.5 54.7
vp9_avg16_neon: 169.9 167.4
vp9_avg32_neon: 585.8 585.2
vp9_avg64_neon: 2460.3 2294.7
vp9_avg_8tap_smooth_4h_neon: 132.7 125.2
vp9_avg_8tap_smooth_4hv_neon: 478.8 442.0
vp9_avg_8tap_smooth_4v_neon: 126.0 93.7
vp9_avg_8tap_smooth_8h_neon: 241.7 234.2
vp9_avg_8tap_smooth_8hv_neon: 690.9 646.5
vp9_avg_8tap_smooth_8v_neon: 245.0 205.5
vp9_avg_8tap_smooth_64h_neon: 11273.2 11280.1
vp9_avg_8tap_smooth_64hv_neon: 22980.6 22184.1
vp9_avg_8tap_smooth_64v_neon: 11549.7 10781.1
vp9_put4_neon: 18.0 17.2
vp9_put8_neon: 40.2 37.7
vp9_put16_neon: 97.4 99.5
vp9_put32_neon/armv8: 346.0 307.4
vp9_put64_neon/armv8: 1319.0 1107.5
vp9_put_8tap_smooth_4h_neon: 126.7 118.2
vp9_put_8tap_smooth_4hv_neon: 465.7 434.0
vp9_put_8tap_smooth_4v_neon: 113.0 86.5
vp9_put_8tap_smooth_8h_neon: 229.7 221.6
vp9_put_8tap_smooth_8hv_neon: 658.9 621.3
vp9_put_8tap_smooth_8v_neon: 215.0 187.5
vp9_put_8tap_smooth_64h_neon: 10636.7 10627.8
vp9_put_8tap_smooth_64hv_neon: 21076.8 21026.9
vp9_put_8tap_smooth_64v_neon: 9635.0 9632.4
These are generally about as fast as the corresponding ARM
routines on the same CPU (at least on the A53), in most cases
marginally faster.
The speedup vs C code is pretty much the same as for the 32 bit
case; on the A53 it's around 6-13x for ther larger 8tap filters.
The exact speedup varies a little, since the C versions generally
don't end up exactly as slow/fast as on 32 bit.
Signed-off-by: Martin Storsjö <martin@martin.st>
Martin Storsjö [Wed, 9 Nov 2016 09:47:57 +0000 (11:47 +0200)]
aarch64: Add an offset parameter to the movrel macro
With apple tools, the linker fails with errors like these, if the
offset is negative:
ld: in section __TEXT,__text reloc 8: symbol index out of range for architecture arm64
Signed-off-by: Martin Storsjö <martin@martin.st>
Martin Storsjö [Sat, 5 Nov 2016 11:18:53 +0000 (13:18 +0200)]
vp9: Make the subpel filters non-static
Make them aligned, to allow efficient access to them from simd.
Signed-off-by: Martin Storsjö <martin@martin.st>
James Almer [Wed, 9 Nov 2016 21:38:24 +0000 (18:38 -0300)]
matroskaenc: write updated STREAMINFO metadata for FLAC streams if available
FLAC streams originating from the FLAC encoder send updated and more
complete STREAMINFO metadata as part of the last packet, so write that
to CodecPrivate instead of the incomplete one available in extradata
during init.
Signed-off-by: James Almer <jamrial@gmail.com>
Signed-off-by: Anton Khirnov <anton@khirnov.net>
James Almer [Wed, 9 Nov 2016 21:38:23 +0000 (18:38 -0300)]
matroskaenc: fix muxing AAC streams when using aac_adtstoasc bsf
aac_adtstoasc makes the aac extradata available only after the first packet
is filtered, and as packet side data.
Assume extradata will be available as part of the first packet if
avpriv_mpeg4audio_get_config() fails the first time due to missing extradata
and reserve space for the OutputSampleRate element in the Tracks master.
Signed-off-by: James Almer <jamrial@gmail.com>
Signed-off-by: Anton Khirnov <anton@khirnov.net>
Anton Khirnov [Mon, 7 Nov 2016 13:21:18 +0000 (14:21 +0100)]
pthread_frame: properly propagate the hw frame context across frame threads
Diego Biurrun [Tue, 8 Nov 2016 17:10:04 +0000 (18:10 +0100)]
mpegaudiodsp: aarch64: Adjust function prototype after
2caa93b813adc5dbb7771dfe615da826a2947d18
Diego Biurrun [Wed, 27 Mar 2013 17:21:10 +0000 (18:21 +0100)]
configure: Move license checks directly after command line parsing
This will allow to error out immediately if incompatible options are
passed on the command line instead of running time-consuming tests.
Diego Biurrun [Tue, 8 Nov 2016 19:04:18 +0000 (20:04 +0100)]
configure: Log name and parameters of all helper functions where it makes sense
Diego Biurrun [Mon, 8 Aug 2016 18:27:43 +0000 (20:27 +0200)]
configure: Use check_cpp in CPP flags tests
Diego Biurrun [Mon, 6 Jun 2016 17:06:30 +0000 (19:06 +0200)]
configure: Log correct test name and use correct filter when testing objective C flags
Diego Biurrun [Mon, 7 Nov 2016 19:22:14 +0000 (20:22 +0100)]
configure: Do not unconditionally check for (and enable) xlib
This avoids unnecessarily linking against xlib.
Diego Biurrun [Mon, 7 Nov 2016 21:12:23 +0000 (22:12 +0100)]
configure: Print list of enabled programs
Also drop a related and now redundant informative output line.
Diego Biurrun [Tue, 25 Oct 2016 20:47:00 +0000 (22:47 +0200)]
configure: Improve output wording
Also drop a redundant output line.
Diego Biurrun [Tue, 8 Nov 2016 16:48:50 +0000 (17:48 +0100)]
avconv: Drop stray leftover debug output
Diego Biurrun [Wed, 16 Dec 2015 17:01:34 +0000 (18:01 +0100)]
Use avpriv_report_missing_feature() where appropriate
Diego Biurrun [Sun, 6 Nov 2016 17:33:05 +0000 (18:33 +0100)]
configure: Add --quiet command line parameter to suppress informative output
Diego Biurrun [Thu, 3 Nov 2016 22:32:45 +0000 (23:32 +0100)]
fate: checkasm: Split monolithic test into individual components
Diego Biurrun [Thu, 3 Nov 2016 22:40:26 +0000 (23:40 +0100)]
checkasm: Add --test parameter to check only specific components
Inspired by a patch from Martin Storsjö <martin@martin.st>.
Vittorio Giovara [Tue, 8 Nov 2016 03:30:22 +0000 (22:30 -0500)]
mov: Read multiple stsd from DV
Signed-off-by: Vittorio Giovara <vittorio.giovara@gmail.com>
Vittorio Giovara [Wed, 2 Nov 2016 16:03:18 +0000 (12:03 -0400)]
hevc: Support extradata changes from multiple stsd
Signed-off-by: Vittorio Giovara <vittorio.giovara@gmail.com>
Vittorio Giovara [Mon, 7 Nov 2016 22:36:20 +0000 (17:36 -0500)]
hevc: Allow parsing external extradata buffers
Vittorio Giovara [Wed, 2 Nov 2016 16:03:17 +0000 (12:03 -0400)]
hevc: Move hevc_decode_extradata before frame decoding
Avoids a forward-declaration in the following commit.
Signed-off-by: Vittorio Giovara <vittorio.giovara@gmail.com>
Vittorio Giovara [Wed, 2 Nov 2016 16:15:16 +0000 (12:15 -0400)]
lavc: Add hevc main10 profile to avconv cli
Vittorio Giovara [Mon, 31 Oct 2016 18:50:59 +0000 (14:50 -0400)]
lavu: Rename ycgco color space appropriately
Planes are ordered as the name suggests now.
Signed-off-by: Vittorio Giovara <vittorio.giovara@gmail.com>
Diego Biurrun [Sun, 3 Jan 2016 21:45:47 +0000 (22:45 +0100)]
h264_qpel: x86: Move function with only one instance out of template macro
libavcodec/x86/h264_qpel.c:392:785: warning: unused function 'ff_avg_h264_qpel8or16_hv1_lowpass_mmxext' [-Wunused-function]
Diego Biurrun [Mon, 9 Nov 2015 11:55:37 +0000 (12:55 +0100)]
avplay: Correct function pointer assignments in options array
avplay.c:2928:5: warning: ISO C forbids initialization between function pointer and ‘void *’ [-Wpedantic]
Diego Biurrun [Mon, 9 Nov 2015 11:54:53 +0000 (12:54 +0100)]
avconv: Correct function pointer assignments in options array
Fixes several warnings of the type
avconv_opt.c:2356:5: warning: ISO C forbids initialization between function pointer and ‘void *’ [-Wpedantic]
Andreas Cadhalpun [Fri, 4 Nov 2016 22:33:02 +0000 (23:33 +0100)]
lzf: update pointer p after realloc
This fixes heap-use-after-free detected by AddressSanitizer.
Signed-off-by: Andreas Cadhalpun <Andreas.Cadhalpun@googlemail.com>
Signed-off-by: Luca Barbato <lu_zero@gentoo.org>
Luca Barbato [Thu, 3 Nov 2016 15:10:03 +0000 (16:10 +0100)]
swscale: Add GRAY12
Luca Barbato [Thu, 3 Nov 2016 15:03:54 +0000 (16:03 +0100)]
pixfmt: Add GRAY12
Anton Khirnov [Wed, 10 Aug 2016 07:38:21 +0000 (09:38 +0200)]
qsv{enc,dec}: extend the internal frame allocator
Handle the internal frame requests, which is required by the HEVC
encoding plugin.
Signed-off-by: Maxym Dmytrychenko <maxym.dmytrychenko@intel.com>
Anton Khirnov [Wed, 10 Aug 2016 06:29:23 +0000 (08:29 +0200)]
qsv{dec,enc}: use a struct as a memory id with internal memory allocator
This will allow implementing the allocator more fully, which is needed
by the HEVC encoder plugin with video memory input.
Signed-off-by: Maxym Dmytrychenko <maxym.dmytrychenko@intel.com>
Anton Khirnov [Tue, 9 Aug 2016 10:05:49 +0000 (12:05 +0200)]
qsv{dec,enc}: always use an internal mfxFrameSurface1
For encoding, this avoids modifying the input surface, which we are not
allowed to do.
This will also be useful in the following commits.
Signed-off-by: Maxym Dmytrychenko <maxym.dmytrychenko@intel.com>
Anton Khirnov [Thu, 6 Oct 2016 09:33:15 +0000 (11:33 +0200)]
hwcontext_qsv: support frame mapping
Signed-off-by: Maxym Dmytrychenko <maxym.dmytrychenko@intel.com>
Anton Khirnov [Wed, 10 Aug 2016 12:58:08 +0000 (14:58 +0200)]
hwcontext_qsv: transfer data through the child context when VPP fails
Uploading/downloading data through VPP may not work for some formats, in
that case we can still try to call av_hwframe_transfer_data() on the
child context.
Signed-off-by: Maxym Dmytrychenko <maxym.dmytrychenko@intel.com>
Anton Khirnov [Wed, 10 Aug 2016 10:54:31 +0000 (12:54 +0200)]
hwcontext_qsv: do not fail when download/upload VPP session creation fails
Certain pixel formats (e.g. P8) might not be supported for
download/upload through VPP operations, but can still be used otherwise.
Signed-off-by: Maxym Dmytrychenko <maxym.dmytrychenko@intel.com>
Anton Khirnov [Wed, 10 Aug 2016 11:01:55 +0000 (13:01 +0200)]
hwcontext_qsv: add support for the P8 format
When using GPU surfaces with QSV, one needs to supply a frame allocator,
which will be invoked to pass surface pools to libmfx.
For encoding, this allocator gets invoked not only for the pool of input
frames, but also for a separate pool of (apparently) reconstructed frames
and another pool of MFX_FOURCC_P8, which on Windows needs to return
D3DFMT_P8 D3D surfaces. Those are probably used to store the encoded
bitstream on the GPU.
Signed-off-by: Maxym Dmytrychenko <maxym.dmytrychenko@intel.com>
Anton Khirnov [Wed, 10 Aug 2016 11:01:55 +0000 (13:01 +0200)]
hwcontext_dxva2: add support for the P8 format
This format is used internally by the QSV encoder to store the encoded
bitstream.
Signed-off-by: Maxym Dmytrychenko <maxym.dmytrychenko@intel.com>
Anton Khirnov [Wed, 5 Oct 2016 11:39:44 +0000 (13:39 +0200)]
hwcontext_dxva2: frame mapping support
Signed-off-by: Maxym Dmytrychenko <maxym.dmytrychenko@intel.com>
Hendrik Leppkes [Mon, 7 Nov 2016 08:59:28 +0000 (09:59 +0100)]
dxva2: fix surface selection when compiled with both d3d11va and dxva2
Fixes a regression introduced in
be630b1e08ebe8f766b1798accd6b8e5e096f5aa
Signed-off-by: Anton Khirnov <anton@khirnov.net>
Derek Buitenhuis [Sun, 6 Nov 2016 14:09:37 +0000 (14:09 +0000)]
libx265: Add option to force IDR frames
This is in the same the same vein as
380146924ecad2e05e9dcc5c3c2e1b5ba47c51e8.
Signed-off-by: Derek Buitenhuis <derek.buitenhuis@gmail.com>
Signed-off-by: Martin Storsjö <martin@martin.st>
Diego Biurrun [Fri, 30 Oct 2015 13:04:08 +0000 (14:04 +0100)]
x86: Drop stray semicolons after function definitions
libavcodec/x86/rv40dsp_init.c:97:2: warning: ISO C does not allow extra ‘;’ outside of a function [-Wpedantic]
libavcodec/x86/vp9dsp_init.c:94:40: warning: ISO C does not allow extra ‘;’ outside of a function [-Wpedantic]
Martin Storsjö [Thu, 3 Nov 2016 12:14:12 +0000 (14:14 +0200)]
configure: Silence lld-link when getting the version number
In recent lld-link versions, this command prints the version to
stdout, but also prints an error to stderr:
$ lld-link -flavor gnu --version
LLD 4.0.0 (trunk 285641)
lld-link: error: no input files
lld-link: error: target emulation unknown: -m or at least one .o file required
Signed-off-by: Martin Storsjö <martin@martin.st>
Martin Storsjö [Fri, 4 Nov 2016 07:16:22 +0000 (09:16 +0200)]
arm: vp9mc: Insert a literal pool at the middle of the file
This fixes errors like this when building non-pic binaries with armv6
as baseline:
Error: invalid literal constant: pool needs to be closer
Signed-off-by: Martin Storsjö <martin@martin.st>
Mark Thompson [Tue, 25 Oct 2016 19:43:08 +0000 (20:43 +0100)]
hwcontext_vaapi: Frame mapping support
Can map to any supported software format (using a GPU copy if it
doesn't actually match the surface format underneath).
Mark Thompson [Tue, 25 Oct 2016 19:40:17 +0000 (20:40 +0100)]
lavfi: Hardware map filter
Takes a frame associated with a hardware context as input and maps it
to something else (another hardware frame or normal memory) for other
processing. If the frame to map was originally in the target format
(but mapped to something else), the original frame is output.
Also supports mapping backwards, where only the output has a hardware
context. The link immediately before will be supplied with mapped
hardware frames which it can write directly into, and this filter
then unmaps them back to the actual hardware frames.
Mark Thompson [Tue, 25 Oct 2016 19:38:47 +0000 (20:38 +0100)]
hwcontext: Hardware frame mapping
Adds the new av_hwframe_map() function, which allows mapping between
hardware frames and normal memory, along with internal support for
implementing it.
Also adds av_hwframe_ctx_create_derived(), for creating a hardware
frames context associated with one device using frames mapped from
another by some hardware-specific means.
Diego Biurrun [Thu, 12 Mar 2015 23:39:31 +0000 (00:39 +0100)]
Drop unreachable break and return statements
Diego Biurrun [Mon, 31 Oct 2016 23:33:05 +0000 (00:33 +0100)]
float_dsp: Have implementation match function pointer prototype
libavutil/x86/float_dsp_init.c(144) : warning C4028: formal parameter 1 different from declaration
libavutil/x86/float_dsp_init.c(144) : warning C4028: formal parameter 2 different from declaration
Diego Biurrun [Mon, 31 Oct 2016 23:30:33 +0000 (00:30 +0100)]
dnxhdenc: Have function pointer prototype match implementation
libavcodec/dnxhdenc.c(326) : warning C4028: formal parameter 1 different from declaration
libavcodec/dnxhdenc.c(329) : warning C4028: formal parameter 1 different from declaration
Diego Biurrun [Mon, 31 Oct 2016 22:12:20 +0000 (23:12 +0100)]
pixblockdsp: Have function pointer prototype match implementation
libavcodec/pixblockdsp.c(58) : warning C4028: formal parameter 1 different from declaration
libavcodec/pixblockdsp.c(63) : warning C4028: formal parameter 1 different from declaration
libavcodec/pixblockdsp.c(66) : warning C4028: formal parameter 1 different from declaration
Diego Biurrun [Mon, 31 Oct 2016 22:06:54 +0000 (23:06 +0100)]
ituh263dec: Have function signature match across declaration and definition
libavcodec/ituh263dec.c(215) : warning C4028: formal parameter 1 different from declaration
libavcodec/ituh263dec.c(215) : warning C4028: formal parameter 2 different from declaration
Mark Thompson [Thu, 3 Nov 2016 16:33:25 +0000 (16:33 +0000)]
vf_hwupload_cuda: Fix build error
Broken by
e3fb74f7f9a8f1895381355f40c92cac3c1023d9.
Signed-off-by: Diego Biurrun <diego@biurrun.de>