|
|
|
|
NAME = avutil
|
|
|
|
|
DESC = FFmpeg utility library
|
|
|
|
|
|
|
|
|
|
HEADERS = adler32.h \
|
|
|
|
|
aes.h \
|
|
|
|
|
aes_ctr.h \
|
|
|
|
|
ambient_viewing_environment.h \
|
|
|
|
|
attributes.h \
|
|
|
|
|
audio_fifo.h \
|
|
|
|
|
avassert.h \
|
|
|
|
|
avstring.h \
|
|
|
|
|
avutil.h \
|
|
|
|
|
base64.h \
|
|
|
|
|
blowfish.h \
|
|
|
|
|
bprint.h \
|
|
|
|
|
bswap.h \
|
|
|
|
|
buffer.h \
|
|
|
|
|
cast5.h \
|
|
|
|
|
camellia.h \
|
|
|
|
|
channel_layout.h \
|
|
|
|
|
common.h \
|
|
|
|
|
cpu.h \
|
|
|
|
|
crc.h \
|
|
|
|
|
csp.h \
|
|
|
|
|
des.h \
|
|
|
|
|
detection_bbox.h \
|
|
|
|
|
dict.h \
|
|
|
|
|
display.h \
|
|
|
|
|
dovi_meta.h \
|
|
|
|
|
downmix_info.h \
|
|
|
|
|
encryption_info.h \
|
|
|
|
|
error.h \
|
|
|
|
|
eval.h \
|
|
|
|
|
executor.h \
|
|
|
|
|
fifo.h \
|
|
|
|
|
file.h \
|
|
|
|
|
frame.h \
|
|
|
|
|
hash.h \
|
|
|
|
|
hdr_dynamic_metadata.h \
|
|
|
|
|
hdr_dynamic_vivid_metadata.h \
|
|
|
|
|
hmac.h \
|
|
|
|
|
hwcontext.h \
|
|
|
|
|
hwcontext_cuda.h \
|
|
|
|
|
hwcontext_d3d11va.h \
|
|
|
|
|
hwcontext_d3d12va.h \
|
|
|
|
|
hwcontext_drm.h \
|
|
|
|
|
hwcontext_dxva2.h \
|
|
|
|
|
hwcontext_qsv.h \
|
|
|
|
|
hwcontext_mediacodec.h \
|
|
|
|
|
hwcontext_opencl.h \
|
|
|
|
|
hwcontext_vaapi.h \
|
|
|
|
|
hwcontext_videotoolbox.h \
|
|
|
|
|
hwcontext_vdpau.h \
|
|
|
|
|
hwcontext_vulkan.h \
|
|
|
|
|
iamf.h \
|
|
|
|
|
imgutils.h \
|
|
|
|
|
intfloat.h \
|
|
|
|
|
intreadwrite.h \
|
|
|
|
|
lfg.h \
|
|
|
|
|
log.h \
|
|
|
|
|
lzo.h \
|
|
|
|
|
macros.h \
|
|
|
|
|
mathematics.h \
|
|
|
|
|
mastering_display_metadata.h \
|
|
|
|
|
md5.h \
|
|
|
|
|
mem.h \
|
|
|
|
|
motion_vector.h \
|
|
|
|
|
murmur3.h \
|
|
|
|
|
opt.h \
|
|
|
|
|
parseutils.h \
|
|
|
|
|
pixdesc.h \
|
|
|
|
|
pixelutils.h \
|
|
|
|
|
pixfmt.h \
|
|
|
|
|
random_seed.h \
|
|
|
|
|
rc4.h \
|
|
|
|
|
rational.h \
|
|
|
|
|
replaygain.h \
|
|
|
|
|
ripemd.h \
|
|
|
|
|
samplefmt.h \
|
|
|
|
|
sha.h \
|
|
|
|
|
sha512.h \
|
|
|
|
|
spherical.h \
|
|
|
|
|
stereo3d.h \
|
|
|
|
|
threadmessage.h \
|
|
|
|
|
time.h \
|
|
|
|
|
timecode.h \
|
|
|
|
|
timestamp.h \
|
|
|
|
|
tree.h \
|
|
|
|
|
twofish.h \
|
|
|
|
|
uuid.h \
|
|
|
|
|
version.h \
|
|
|
|
|
video_enc_params.h \
|
|
|
|
|
xtea.h \
|
|
|
|
|
tea.h \
|
libavutil: add an FFT & MDCT implementation
This commit adds a new API to libavutil to allow for arbitrary transformations
on various types of data.
This is a partly new implementation, with the power of two transforms taken
from libavcodec/fft_template, the 5 and 15-point FFT taken from mdct15, while
the 3-point FFT was written from scratch.
The (i)mdct folding code is taken from mdct15 as well, as the mdct_template
code was somewhat old, messy and not easy to separate.
A notable feature of this implementation is that it allows for 3xM and 5xM
based transforms, where M is a power of two, e.g. 384, 640, 768, 1280, etc.
AC-4 uses 3xM transforms while Siren uses 5xM transforms, so the code will
allow for decoding of such streams.
A non-exaustive list of supported sizes:
4, 8, 12, 16, 20, 24, 32, 40, 48, 60, 64, 80, 96, 120, 128, 160, 192, 240,
256, 320, 384, 480, 512, 640, 768, 960, 1024, 1280, 1536, 1920, 2048, 2560...
The API was designed such that it allows for not only 1D transforms but also
2D transforms of certain block sizes. This was partly on accident as the stride
argument is required for Opus MDCTs, but can be used in the context of a 2D
transform as well.
Also, various data types would be implemented eventually as well, such as
"double" and "int32_t".
Some performance comparisons with libfftw3f (SIMD disabled for both):
120:
22353 decicycles in fftwf_execute, 1024 runs, 0 skips
21836 decicycles in compound_fft_15x8, 1024 runs, 0 skips
128:
22003 decicycles in fftwf_execute, 1024 runs, 0 skips
23132 decicycles in monolithic_fft_ptwo, 1024 runs, 0 skips
384:
75939 decicycles in fftwf_execute, 1024 runs, 0 skips
73973 decicycles in compound_fft_3x128, 1024 runs, 0 skips
640:
104354 decicycles in fftwf_execute, 1024 runs, 0 skips
149518 decicycles in compound_fft_5x128, 1024 runs, 0 skips
768:
109323 decicycles in fftwf_execute, 1024 runs, 0 skips
164096 decicycles in compound_fft_3x256, 1024 runs, 0 skips
960:
186210 decicycles in fftwf_execute, 1024 runs, 0 skips
215256 decicycles in compound_fft_15x64, 1024 runs, 0 skips
1024:
163464 decicycles in fftwf_execute, 1024 runs, 0 skips
199686 decicycles in monolithic_fft_ptwo, 1024 runs, 0 skips
With SIMD we should be faster than fftw for 15xM transforms as our fft15 SIMD
is around 2x faster than theirs, even if our ptwo SIMD is slightly slower.
The goal is to remove the libavcodec/mdct15 code and deprecate the
libavcodec/avfft interface once aarch64 and x86 SIMD code has been ported.
New code throughout the project should use this API.
The implementation passes fate when used in Opus, AAC and Vorbis, and the output
is identical with ATRAC9 as well.
6 years ago
|
|
|
tx.h \
|
|
|
|
|
film_grain_params.h \
|
|
|
|
|
video_hint.h
|
|
|
|
|
|
|
|
|
|
ARCH_HEADERS = bswap.h \
|
|
|
|
|
intmath.h \
|
|
|
|
|
intreadwrite.h \
|
|
|
|
|
timer.h \
|
|
|
|
|
|
|
|
|
|
BUILT_HEADERS = avconfig.h \
|
|
|
|
|
ffversion.h
|
|
|
|
|
|
|
|
|
|
OBJS = adler32.o \
|
|
|
|
|
aes.o \
|
|
|
|
|
aes_ctr.o \
|
|
|
|
|
ambient_viewing_environment.o \
|
|
|
|
|
audio_fifo.o \
|
|
|
|
|
avstring.o \
|
|
|
|
|
avsscanf.o \
|
|
|
|
|
base64.o \
|
|
|
|
|
blowfish.o \
|
|
|
|
|
bprint.o \
|
|
|
|
|
buffer.o \
|
|
|
|
|
cast5.o \
|
|
|
|
|
camellia.o \
|
|
|
|
|
channel_layout.o \
|
|
|
|
|
cpu.o \
|
|
|
|
|
crc.o \
|
|
|
|
|
csp.o \
|
|
|
|
|
des.o \
|
|
|
|
|
detection_bbox.o \
|
|
|
|
|
dict.o \
|
|
|
|
|
display.o \
|
|
|
|
|
dovi_meta.o \
|
|
|
|
|
downmix_info.o \
|
|
|
|
|
encryption_info.o \
|
|
|
|
|
error.o \
|
|
|
|
|
eval.o \
|
|
|
|
|
executor.o \
|
|
|
|
|
fifo.o \
|
|
|
|
|
file.o \
|
|
|
|
|
file_open.o \
|
|
|
|
|
float_dsp.o \
|
|
|
|
|
fixed_dsp.o \
|
|
|
|
|
frame.o \
|
|
|
|
|
hash.o \
|
|
|
|
|
hdr_dynamic_metadata.o \
|
|
|
|
|
hdr_dynamic_vivid_metadata.o \
|
|
|
|
|
hmac.o \
|
|
|
|
|
hwcontext.o \
|
|
|
|
|
iamf.o \
|
|
|
|
|
imgutils.o \
|
|
|
|
|
integer.o \
|
|
|
|
|
intmath.o \
|
|
|
|
|
lfg.o \
|
|
|
|
|
lls.o \
|
|
|
|
|
log.o \
|
|
|
|
|
log2_tab.o \
|
|
|
|
|
lzo.o \
|
|
|
|
|
mathematics.o \
|
|
|
|
|
mastering_display_metadata.o \
|
|
|
|
|
md5.o \
|
|
|
|
|
mem.o \
|
|
|
|
|
murmur3.o \
|
|
|
|
|
opt.o \
|
|
|
|
|
parseutils.o \
|
|
|
|
|
pixdesc.o \
|
|
|
|
|
pixelutils.o \
|
|
|
|
|
random_seed.o \
|
|
|
|
|
rational.o \
|
|
|
|
|
reverse.o \
|
|
|
|
|
rc4.o \
|
|
|
|
|
ripemd.o \
|
|
|
|
|
samplefmt.o \
|
|
|
|
|
sha.o \
|
|
|
|
|
sha512.o \
|
|
|
|
|
slicethread.o \
|
|
|
|
|
spherical.o \
|
|
|
|
|
stereo3d.o \
|
|
|
|
|
threadmessage.o \
|
|
|
|
|
time.o \
|
|
|
|
|
timecode.o \
|
avutil/timestamp: introduce av_ts_make_time_string2 for better precision
av_ts_make_time_string() used "%.6g" format, but this format was losing
precision even when the timestamp to be printed was not that large. For example
for 3 hours (10800) seconds, only 1 decimal digit was printed, which made this
format inaccurate when it was used in e.g. the silencedetect filter. Other
detection filters printing timestamps had similar issues. Also time base
parameter of the function was *AVRational instead of AVRational.
Resolve these problems by introducing a new function, av_ts_make_time_string2().
We change the used format to "%.*f", use a precision of 6, except when printing
values near 0, in which case we calculate the precision dynamically to aim for
a similar precision in normal form as with %.6g. No longer using scientific
representation can make parsing the timestamp easier for the users, we can
safely do this because the theoretical maximum of INT64_MAX*INT32_MAX still
fits into the string buffer in normal form.
We somewhat imitate %g by trimming ending zeroes and the potential decimal
point characters. In order not to trim "inf" as well, we assume that the
decimal point string does not contain the letter "f". Note that depending on
printf %f implementation, we might trim "infinity" to "inf".
Thanks for Allan Cady for bringing up this issue.
Signed-off-by: Marton Balint <cus@passwd.hu>
10 months ago
|
|
|
timestamp.o \
|
|
|
|
|
tree.o \
|
|
|
|
|
twofish.o \
|
|
|
|
|
utils.o \
|
|
|
|
|
xga_font_data.o \
|
|
|
|
|
xtea.o \
|
|
|
|
|
tea.o \
|
libavutil: add an FFT & MDCT implementation
This commit adds a new API to libavutil to allow for arbitrary transformations
on various types of data.
This is a partly new implementation, with the power of two transforms taken
from libavcodec/fft_template, the 5 and 15-point FFT taken from mdct15, while
the 3-point FFT was written from scratch.
The (i)mdct folding code is taken from mdct15 as well, as the mdct_template
code was somewhat old, messy and not easy to separate.
A notable feature of this implementation is that it allows for 3xM and 5xM
based transforms, where M is a power of two, e.g. 384, 640, 768, 1280, etc.
AC-4 uses 3xM transforms while Siren uses 5xM transforms, so the code will
allow for decoding of such streams.
A non-exaustive list of supported sizes:
4, 8, 12, 16, 20, 24, 32, 40, 48, 60, 64, 80, 96, 120, 128, 160, 192, 240,
256, 320, 384, 480, 512, 640, 768, 960, 1024, 1280, 1536, 1920, 2048, 2560...
The API was designed such that it allows for not only 1D transforms but also
2D transforms of certain block sizes. This was partly on accident as the stride
argument is required for Opus MDCTs, but can be used in the context of a 2D
transform as well.
Also, various data types would be implemented eventually as well, such as
"double" and "int32_t".
Some performance comparisons with libfftw3f (SIMD disabled for both):
120:
22353 decicycles in fftwf_execute, 1024 runs, 0 skips
21836 decicycles in compound_fft_15x8, 1024 runs, 0 skips
128:
22003 decicycles in fftwf_execute, 1024 runs, 0 skips
23132 decicycles in monolithic_fft_ptwo, 1024 runs, 0 skips
384:
75939 decicycles in fftwf_execute, 1024 runs, 0 skips
73973 decicycles in compound_fft_3x128, 1024 runs, 0 skips
640:
104354 decicycles in fftwf_execute, 1024 runs, 0 skips
149518 decicycles in compound_fft_5x128, 1024 runs, 0 skips
768:
109323 decicycles in fftwf_execute, 1024 runs, 0 skips
164096 decicycles in compound_fft_3x256, 1024 runs, 0 skips
960:
186210 decicycles in fftwf_execute, 1024 runs, 0 skips
215256 decicycles in compound_fft_15x64, 1024 runs, 0 skips
1024:
163464 decicycles in fftwf_execute, 1024 runs, 0 skips
199686 decicycles in monolithic_fft_ptwo, 1024 runs, 0 skips
With SIMD we should be faster than fftw for 15xM transforms as our fft15 SIMD
is around 2x faster than theirs, even if our ptwo SIMD is slightly slower.
The goal is to remove the libavcodec/mdct15 code and deprecate the
libavcodec/avfft interface once aarch64 and x86 SIMD code has been ported.
New code throughout the project should use this API.
The implementation passes fate when used in Opus, AAC and Vorbis, and the output
is identical with ATRAC9 as well.
6 years ago
|
|
|
tx.o \
|
|
|
|
|
tx_float.o \
|
|
|
|
|
tx_double.o \
|
|
|
|
|
tx_int32.o \
|
|
|
|
|
uuid.o \
|
|
|
|
|
version.o \
|
|
|
|
|
video_enc_params.o \
|
|
|
|
|
video_hint.o \
|
|
|
|
|
film_grain_params.o \
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
OBJS-$(CONFIG_CUDA) += hwcontext_cuda.o
|
|
|
|
|
OBJS-$(CONFIG_D3D11VA) += hwcontext_d3d11va.o
|
|
|
|
|
OBJS-$(CONFIG_D3D12VA) += hwcontext_d3d12va.o
|
|
|
|
|
OBJS-$(CONFIG_DXVA2) += hwcontext_dxva2.o
|
|
|
|
|
OBJS-$(CONFIG_LIBDRM) += hwcontext_drm.o
|
|
|
|
|
OBJS-$(CONFIG_MACOS_KPERF) += macos_kperf.o
|
|
|
|
|
OBJS-$(CONFIG_MEDIACODEC) += hwcontext_mediacodec.o
|
|
|
|
|
OBJS-$(CONFIG_OPENCL) += hwcontext_opencl.o
|
|
|
|
|
OBJS-$(CONFIG_QSV) += hwcontext_qsv.o
|
|
|
|
|
OBJS-$(CONFIG_VAAPI) += hwcontext_vaapi.o
|
|
|
|
|
OBJS-$(CONFIG_VIDEOTOOLBOX) += hwcontext_videotoolbox.o
|
|
|
|
|
OBJS-$(CONFIG_VDPAU) += hwcontext_vdpau.o
|
|
|
|
|
OBJS-$(CONFIG_VULKAN) += hwcontext_vulkan.o vulkan.o
|
|
|
|
|
|
|
|
|
|
OBJS-$(!CONFIG_VULKAN) += hwcontext_stub.o
|
|
|
|
|
|
|
|
|
|
OBJS += $(COMPAT_OBJS:%=../compat/%)
|
|
|
|
|
|
|
|
|
|
# Windows resource file
|
|
|
|
|
SHLIBOBJS-$(HAVE_GNU_WINDRES) += avutilres.o
|
|
|
|
|
|
|
|
|
|
SKIPHEADERS += objc.h
|
|
|
|
|
SKIPHEADERS-$(HAVE_CUDA_H) += hwcontext_cuda.h
|
|
|
|
|
SKIPHEADERS-$(CONFIG_CUDA) += hwcontext_cuda_internal.h \
|
|
|
|
|
cuda_check.h
|
|
|
|
|
SKIPHEADERS-$(CONFIG_D3D11VA) += hwcontext_d3d11va.h
|
|
|
|
|
SKIPHEADERS-$(CONFIG_D3D12VA) += hwcontext_d3d12va.h
|
|
|
|
|
SKIPHEADERS-$(CONFIG_DXVA2) += hwcontext_dxva2.h
|
|
|
|
|
SKIPHEADERS-$(CONFIG_QSV) += hwcontext_qsv.h
|
|
|
|
|
SKIPHEADERS-$(CONFIG_OPENCL) += hwcontext_opencl.h
|
|
|
|
|
SKIPHEADERS-$(CONFIG_VAAPI) += hwcontext_vaapi.h
|
|
|
|
|
SKIPHEADERS-$(CONFIG_VIDEOTOOLBOX) += hwcontext_videotoolbox.h
|
|
|
|
|
SKIPHEADERS-$(CONFIG_VDPAU) += hwcontext_vdpau.h
|
|
|
|
|
SKIPHEADERS-$(CONFIG_VULKAN) += hwcontext_vulkan.h vulkan.h \
|
|
|
|
|
vulkan_functions.h \
|
|
|
|
|
vulkan_loader.h
|
|
|
|
|
|
|
|
|
|
TESTPROGS = adler32 \
|
|
|
|
|
aes \
|
|
|
|
|
aes_ctr \
|
|
|
|
|
audio_fifo \
|
|
|
|
|
avstring \
|
|
|
|
|
base64 \
|
|
|
|
|
blowfish \
|
|
|
|
|
bprint \
|
|
|
|
|
cast5 \
|
|
|
|
|
camellia \
|
|
|
|
|
channel_layout \
|
|
|
|
|
color_utils \
|
|
|
|
|
cpu \
|
|
|
|
|
crc \
|
|
|
|
|
des \
|
|
|
|
|
dict \
|
|
|
|
|
display \
|
|
|
|
|
encryption_info \
|
|
|
|
|
error \
|
|
|
|
|
eval \
|
|
|
|
|
file \
|
|
|
|
|
fifo \
|
|
|
|
|
hash \
|
|
|
|
|
hmac \
|
|
|
|
|
hwdevice \
|
|
|
|
|
integer \
|
|
|
|
|
imgutils \
|
|
|
|
|
lfg \
|
|
|
|
|
lls \
|
|
|
|
|
log \
|
|
|
|
|
md5 \
|
|
|
|
|
murmur3 \
|
|
|
|
|
opt \
|
|
|
|
|
pca \
|
|
|
|
|
parseutils \
|
|
|
|
|
pixdesc \
|
|
|
|
|
pixelutils \
|
|
|
|
|
pixfmt_best \
|
|
|
|
|
random_seed \
|
|
|
|
|
rational \
|
|
|
|
|
ripemd \
|
|
|
|
|
sha \
|
|
|
|
|
sha512 \
|
|
|
|
|
side_data_array \
|
|
|
|
|
softfloat \
|
|
|
|
|
tree \
|
|
|
|
|
twofish \
|
|
|
|
|
utf8 \
|
|
|
|
|
uuid \
|
|
|
|
|
xtea \
|
|
|
|
|
tea \
|
|
|
|
|
|
|
|
|
|
TESTPROGS-$(HAVE_THREADS) += cpu_init
|
|
|
|
|
TESTPROGS-$(HAVE_LZO1X_999_COMPRESS) += lzo
|
|
|
|
|
|
|
|
|
|
TOOLS = crypto_bench ffhash ffeval ffescape
|
|
|
|
|
|
|
|
|
|
tools/crypto_bench$(EXESUF): ELIBS += $(if $(VERSUS),$(subst +, -l,+$(VERSUS)),)
|
|
|
|
|
tools/crypto_bench.o: CFLAGS += -DUSE_EXT_LIBS=0$(if $(VERSUS),$(subst +,+USE_,+$(VERSUS)),)
|
|
|
|
|
|
|
|
|
|
$(SUBDIR)tests/lzo$(EXESUF): ELIBS = -llzo2
|
