This adds a property to select the maximum number of threads to use for
conversion and scaling. During processing, each plane is split into
an equal number of consecutive lines that are then processed by each
thread.
During tests, this gave up to 1.8x speedup with 2 threads and up to 3.2x
speedup with 4 threads when converting e.g. 1080p to 4k in v210.
https://bugzilla.gnome.org/show_bug.cgi?id=778974
https://github.com/mesonbuild/meson
With contributions from:
Tim-Philipp Müller <tim@centricular.com>
Jussi Pakkanen <jpakkane@gmail.com> (original port)
Highlights of the features provided are:
* Faster builds on Linux (~40-50% faster)
* The ability to build with MSVC on Windows
* Generate Visual Studio project files
* Generate XCode project files
* Much faster builds on Windows (on-par with Linux)
* Seriously fast configure and building on embedded
... and many more. For more details see:
http://blog.nirbheek.in/2016/05/gstreamer-and-meson-new-hope.htmlhttp://blog.nirbheek.in/2016/07/building-and-developing-gstreamer-using.html
Building with Meson should work on both Linux and Windows, but may
need a few more tweaks on other operating systems.
libgstreamer currently exports some debug category
symbols GST_CAT_*, but those are not declared in any
public headers.
Some plugins and libgstvideo just use GST_DEBUG_CATEGORY_EXTERN()
to declare and use those, but that's just not right at
all, and it won't work on Windows with MSVC. Instead look
up the categories via the API.
Move the conversion code used in videoconvert to the video library
and expose a simple but generic API to do arbitrary conversion. It can
currently do colorspace conversion but the plan is to add videoscale to
it as well.
See https://bugzilla.gnome.org/show_bug.cgi?id=732415
Make a little table of conversions and manually score them. Use this
info to define better weights for the scoring algorithm.
give separate scores for doing changes and the impact of the change,
This allows us to avoid conversion when we can but still allow fairly
lossless changes.
The old code did not penalize GRAY conversions, PAL conversions were
punished too low and depth conversions too high.
Fixes https://bugzilla.gnome.org/show_bug.cgi?id=722656
Don't try to interpolate the chroma samples, the used algorithm only
works for horizontal cositing. Let's switch to a faster and safer
version until we handle chroma siting correctly in the fastpaths.
Rework the orc code to be around 10% faster and support arbitrary matrices.
Pass the matrix parameters to the YUV->RGB functions to make them work
for all matrices. This enables more and faster fastpath conversions.
See https://bugzilla.gnome.org/show_bug.cgi?id=721701
This fast-path was adding 128 to every component including
alpha while it should only be done for all components except
alpha. This caused wrong alpha values to be generated.
Also remove the high-quality I420 to BGRA fast-path as it needs
the same fix, which causes an additional instruction, which causes
orc to emit more than 96 variables, which then just crashes.
This can only be fixed in orc by breaking ABI and allowing more
variables.
Some of the fastpath function can only work with aligned widht/height
so make sure we check this as well when choosing a fastpath.
Add fastpath for I420/YV12 -> BGRx
Increase the number of temporary lines that we need, it is possible that the
up and downsampling offsets are out of phase and that we need to keep some
extra lines around. Also copy the unhandled output lines for the next round
instead of overwriting them.
Fixes https://bugzilla.gnome.org/show_bug.cgi?id=706823
Try to select the conversion that would result in the minimal amount of quality
loss. Quality loss is calculated rather arbitrarily but it avoids doing
something really stupid in most cases.
