]>
git.sesse.net Git - movit/log
Steinar H. Gunderson [Wed, 22 Nov 2017 18:28:14 +0000 (19:28 +0100)]
Do some more cleanups in anticipation of more flexible compute shader outputs.
Includes reverting back to last_phase instead of render_to_texture.
Steinar H. Gunderson [Tue, 21 Nov 2017 23:04:03 +0000 (00:04 +0100)]
Support rendering compute shaders straight to textures (skipping the dummy phase).
There are lots of limitations currently (only one destination,
only GL_RGBA16F), but it's a good start. Curiously enough,
it doesn't really help anything on the deinterlacing benchmark
for my Haswell, but NVIDIA sees ~15% improvement.
Steinar H. Gunderson [Mon, 20 Nov 2017 23:57:51 +0000 (00:57 +0100)]
Fix an issue where -std=gnu++11 would become the only flag.
Steinar H. Gunderson [Mon, 20 Nov 2017 18:41:10 +0000 (19:41 +0100)]
Add a texture barrier after dispatching each compute shader.
This is maybe a bit heavy-handed (there are cases where shaders could
run in parallel), but it's by far the simplest thing to do, since we
have zero control over what happens to the textures we use when they
are handed back to the resource pool.
Steinar H. Gunderson [Mon, 20 Nov 2017 18:10:47 +0000 (19:10 +0100)]
Add some asserts to EffectChain::execute_phase, so that we do not inadvertedly insert new output textures with number 0.
Steinar H. Gunderson [Mon, 20 Nov 2017 18:07:46 +0000 (19:07 +0100)]
Invert the meaning of the last_phase boolean to execute_phase().
This is because we can soon have last phases that do not render to FBOs
(those that come out of compute shaders).
Steinar H. Gunderson [Mon, 20 Nov 2017 17:27:22 +0000 (18:27 +0100)]
Use glGetTexImage() instead of glReadPixels() for reading back test data.
Generally cleaner, and also paves the way for when we have FBO-less
rendering from compute shaders.
Steinar H. Gunderson [Sun, 19 Nov 2017 14:25:30 +0000 (15:25 +0100)]
Better error messages when skipping compute shader benchmarks.
Steinar H. Gunderson [Thu, 16 Nov 2017 22:07:47 +0000 (23:07 +0100)]
Implement a compute shdaer version of DeinterlaceEffect.
This is currently a loss for grayscale (probably due to the extra
rgba16f bounce), but a win of about ~30% on BGRA on my Haswell.
NVIDIA doesn't care much either way.
There are some performance mysteries remaining, but it's a good start.
Steinar H. Gunderson [Sun, 19 Nov 2017 00:32:06 +0000 (01:32 +0100)]
Reduce the clutter in instantiating benchmarks a little bit.
Steinar H. Gunderson [Sun, 19 Nov 2017 00:28:02 +0000 (01:28 +0100)]
Add a helper class to easier test fragment and compute shader versions of the same effect alongside each other.
Steinar H. Gunderson [Sat, 18 Nov 2017 20:20:06 +0000 (21:20 +0100)]
Fix compute shader outputs on NVIDIA.
Steinar H. Gunderson [Sat, 18 Nov 2017 20:13:14 +0000 (21:13 +0100)]
Bump compute shader header to #version 150.
NVIDIA requires this for the layout qualifier, and it's probably right.
Note that this required moving the unit tests to a core context,
due to Mesa's demands.
Steinar H. Gunderson [Sat, 18 Nov 2017 20:11:07 +0000 (21:11 +0100)]
Drop support for SDL1, which is no longer maintained.
Steinar H. Gunderson [Sat, 18 Nov 2017 17:24:08 +0000 (18:24 +0100)]
Use auto and range-based for loops a few places where it aids clarity.
Steinar H. Gunderson [Sat, 18 Nov 2017 13:44:51 +0000 (14:44 +0100)]
More renaming of .compute -> .comp.
Steinar H. Gunderson [Sat, 18 Nov 2017 10:45:30 +0000 (11:45 +0100)]
Fix an issue where matrices would not get printed out on test failure.
Steinar H. Gunderson [Sat, 18 Nov 2017 10:35:15 +0000 (11:35 +0100)]
Add a benchmark for DeinterlaceTest without the spatial interlacing check.
Steinar H. Gunderson [Sat, 18 Nov 2017 10:07:37 +0000 (11:07 +0100)]
Rename .compute to .comp, to be in line with the Khronos reference compiler.
Steinar H. Gunderson [Fri, 17 Nov 2017 20:41:39 +0000 (21:41 +0100)]
Make BGRA deinterlacing benchmark premultiplied, so that we do not use forever just in bouncing.
Steinar H. Gunderson [Thu, 16 Nov 2017 17:17:28 +0000 (18:17 +0100)]
Parametrize BM_DeinterlaceEffect so that we have both grayscale and BGRA.
Steinar H. Gunderson [Wed, 15 Nov 2017 23:34:47 +0000 (00:34 +0100)]
Fix deletion of compute shaders.
Steinar H. Gunderson [Wed, 15 Nov 2017 19:49:59 +0000 (20:49 +0100)]
Fix some missing NULL -> nullptr.
Steinar H. Gunderson [Wed, 15 Nov 2017 19:47:31 +0000 (20:47 +0100)]
Revert "Remove C++11 dependency from ResampleEffect."
Add back unique_ptr, now that we have C++11.
This reverts commit
8e9f58fec54a4c879035b214fd7411f6ff7b3a32 .
Steinar H. Gunderson [Wed, 15 Nov 2017 19:46:16 +0000 (20:46 +0100)]
Use double right angle brackets for nested templates everywhere, now that we have C++11.
Steinar H. Gunderson [Wed, 15 Nov 2017 19:45:41 +0000 (20:45 +0100)]
Use nullptr everywhere, now that we have C++11.
Steinar H. Gunderson [Wed, 15 Nov 2017 19:30:58 +0000 (20:30 +0100)]
Add support for microbenchmarks.
This depends on Google's microbenchmark library (latest git version,
at least as soon as they pull in the pkg-config file), but it is
not mandatory.
Note that this makes Movit depend on C++11.
Steinar H. Gunderson [Mon, 13 Nov 2017 20:58:40 +0000 (21:58 +0100)]
Add support for compute shaders.
This is currently pretty raw, and there are no effect using it yet,
but it's a useful first step for getting the infrastructure in place.
Steinar H. Gunderson [Mon, 13 Nov 2017 19:36:27 +0000 (20:36 +0100)]
There's no need to #undef PREFIX, since we do the token pasting ourselves.
Steinar H. Gunderson [Sun, 12 Nov 2017 00:30:01 +0000 (01:30 +0100)]
Fix some invalid code in DeinterlaceTest; GCC 7 would optimize it into simply an infinite loop.
Steinar H. Gunderson [Sat, 11 Nov 2017 21:02:46 +0000 (22:02 +0100)]
Some refactoring in ResourcePool.
Steinar H. Gunderson [Sat, 16 Sep 2017 10:08:27 +0000 (12:08 +0200)]
Add the GPLv2 license text.
Pascal Massimino [Thu, 14 Sep 2017 10:58:57 +0000 (12:58 +0200)]
fix compile error: "error: variable-sized object ‘red_data’ may not be initialized"
Steinar H. Gunderson [Wed, 13 Sep 2017 18:28:26 +0000 (20:28 +0200)]
Support negative values for lift in LiftGammaGainEffect.
Patch by Jean-Baptiste Mardelle <jb@kdenlive.org> (except the test,
which is by myself). Based on work from Dušan Hanuš <hanus@pixelhouse.cz>.
Steinar H. Gunderson [Thu, 10 Aug 2017 23:09:13 +0000 (01:09 +0200)]
Fix a typo.
Steinar H. Gunderson [Thu, 10 Aug 2017 15:59:58 +0000 (17:59 +0200)]
Release Movit 1.5.3.
Steinar H. Gunderson [Tue, 8 Aug 2017 16:03:09 +0000 (18:03 +0200)]
Add a notice to render_to_screen() that it might be suboptimal.
Steinar H. Gunderson [Mon, 7 Aug 2017 07:32:21 +0000 (09:32 +0200)]
Fix a leak if ResampleEffect is destroyed before being put on a chain.
FFTConvolutionEffect remembered this, but ResampleEffect did not.
Patch by Dan Dennedy.
Steinar H. Gunderson [Thu, 3 Aug 2017 13:36:30 +0000 (15:36 +0200)]
Fix fp16_test compilation _without_ f16c-enabled compilation flags.
Reported by Arthur Huillet.
Steinar H. Gunderson [Tue, 1 Aug 2017 15:41:17 +0000 (17:41 +0200)]
Fix fp16_test compilation with f16c-enabled compilation flags.
Steinar H. Gunderson [Tue, 1 Aug 2017 07:25:10 +0000 (09:25 +0200)]
Remove C++11 dependency from ResampleEffect.
We really ought to allow C++11 in Movit soon, but 1.5.2 is not the right release.
Reported by Etienne d'Hautefeuille.
Steinar H. Gunderson [Fri, 28 Jul 2017 17:06:33 +0000 (19:06 +0200)]
Fix a double-unlock.
Steinar H. Gunderson [Wed, 5 Jul 2017 07:37:39 +0000 (09:37 +0200)]
Release Movit 1.5.2.
Steinar H. Gunderson [Wed, 5 Jul 2017 07:35:40 +0000 (09:35 +0200)]
Add some room for future expansion in ResampleEffect, since I have something that I would like them for and we are breaking the ABI anyway.
Steinar H. Gunderson [Tue, 4 Jul 2017 23:06:12 +0000 (01:06 +0200)]
Cache VAOs between runs.
NVIDIA's drivers (at least the Linux drivers) seem to have a bug
where, if you call glVertexAttribPointer() in one thread together
with some specific activity in another thread (at least another
glVertexAttribPointer() will do, but I've also seen it during
glXSwapBuffers()), it will try to free a non-malloced pointer,
crashing everything. This happens very rarely, but often enough
that it's a real problem for Nageru.
We solve it by simply pre-creating all needed VAOs ahead-of-time
and caching them, which makes us call glVertexAttribPointer()
a _lot_ less often (basically never, instead of several times
per frame). This might actually be a bit slower than the old code
(I haven't tested), but at least it works around the driver bug.
ABI break, unfortunately, but no API break.
Steinar H. Gunderson [Sun, 2 Jul 2017 09:32:34 +0000 (11:32 +0200)]
Fix Makefile after fp16 removal.
Steinar H. Gunderson [Sun, 2 Jul 2017 08:18:34 +0000 (10:18 +0200)]
Inline the fp16 conversion routines. Helps 18% on ResampleEffect::calculate_texture.
Steinar H. Gunderson [Sun, 2 Jul 2017 08:10:11 +0000 (10:10 +0200)]
Inline combine_two_samples (and remove an obsolete assert). Helps 13–14% on ResampleEffect::calculate_texture.
Steinar H. Gunderson [Sun, 2 Jul 2017 08:06:54 +0000 (10:06 +0200)]
Some microoptimizations in combine_two_samples(). Saves about 4% in ResampleEffect::calculate_weights.
Steinar H. Gunderson [Sat, 1 Jul 2017 19:50:31 +0000 (21:50 +0200)]
Remove some unneeded conversions from ResampleEffect. Speeds up texture generation by ~8%.
Steinar H. Gunderson [Sat, 1 Jul 2017 19:07:32 +0000 (21:07 +0200)]
In ResampleEffect, split the weight calculation out into its own function that does not depend on OpenGL.
Steinar H. Gunderson [Mon, 29 May 2017 17:09:00 +0000 (19:09 +0200)]
Release Movit 1.5.1. (No ABI break, as only a new non-virtual member function is added.)
Steinar H. Gunderson [Sat, 20 May 2017 10:44:32 +0000 (12:44 +0200)]
Fix multiply-defined symbols with multiple YCbCrInputs in the same chain.
Steinar H. Gunderson [Sat, 29 Apr 2017 19:59:38 +0000 (21:59 +0200)]
Allow YCbCrInput to change input format after finalize.
The performance should be very nearly identical; only a little
possible constant folding, and that's it. There's only one
(documented) limitation, and it's both rare and should be easy
to work around.
Steinar H. Gunderson [Sat, 29 Apr 2017 18:55:49 +0000 (20:55 +0200)]
In YCbCrInput, fix an issue where offsets would be treated as equal even if their y value differed.
Steinar H. Gunderson [Tue, 11 Apr 2017 19:55:10 +0000 (21:55 +0200)]
Add a warning on FlatInput::set_texture_num() about sRGB behavior.
Steinar H. Gunderson [Tue, 21 Mar 2017 18:39:51 +0000 (19:39 +0100)]
Release Movit 1.5.0, including a small README update.
Steinar H. Gunderson [Wed, 15 Mar 2017 19:03:05 +0000 (20:03 +0100)]
Loosen a test bound slightly for the benefit of NVIDIA cards.
Steinar H. Gunderson [Mon, 13 Mar 2017 22:32:36 +0000 (23:32 +0100)]
Add an explanatory comment about dither with 16-bit output.
Steinar H. Gunderson [Mon, 13 Mar 2017 19:12:50 +0000 (20:12 +0100)]
Support 10-/12-bit Y'CbCr output packed in 16-bit.
This mirrors our existing input support, and makes planar and
semiplanar output possible for 10-/12-bit Y'CbCr.
ABI break. API stays the same.
Steinar H. Gunderson [Tue, 7 Mar 2017 23:28:18 +0000 (00:28 +0100)]
Don't try to check Cb and Cr positioning for output formats, as they should be non-subsampled anyway.
Steinar H. Gunderson [Mon, 6 Mar 2017 23:02:18 +0000 (00:02 +0100)]
Support multiple Y'CbCr outputs.
This is rather limited for now, unfortunately, but it solves a
rather specific problem in Nageru.
Steinar H. Gunderson [Mon, 6 Mar 2017 18:52:28 +0000 (19:52 +0100)]
Update another outdated comment.
Steinar H. Gunderson [Mon, 6 Mar 2017 18:51:48 +0000 (19:51 +0100)]
Update an outdated comment.
Steinar H. Gunderson [Sun, 26 Feb 2017 15:15:10 +0000 (16:15 +0100)]
Loosen up the accuracy bounds a tiny bit in some tests for NVIDIA cards, which have worse rounding (we do not bother to add manual rounding for these cards, since the difference is so small).
Steinar H. Gunderson [Sun, 26 Feb 2017 15:10:47 +0000 (16:10 +0100)]
Fix an issue where the last pass would have been rendered with the sRGB flag set, which confused Qt applications running in certain NVIDIA configurations.
Steinar H. Gunderson [Mon, 20 Feb 2017 20:44:33 +0000 (21:44 +0100)]
Fix compiling without C++11.
ABI break. Reported by Dan Dennedy.
Steinar H. Gunderson [Mon, 20 Feb 2017 18:56:53 +0000 (19:56 +0100)]
Fix a bad typo.
Steinar H. Gunderson [Sun, 19 Feb 2017 19:35:31 +0000 (20:35 +0100)]
Bump MOVIT_VERSION for all the YCbCr changes.
Steinar H. Gunderson [Sun, 19 Feb 2017 19:35:19 +0000 (20:35 +0100)]
Treat num_levels == 0 as 256, for the benefit of older applications.
Steinar H. Gunderson [Sun, 19 Feb 2017 15:55:44 +0000 (16:55 +0100)]
Cosmetic tweak in YCbCrInput.
Steinar H. Gunderson [Sun, 19 Feb 2017 15:55:33 +0000 (16:55 +0100)]
Fix a stack buffer overrun in ycbcr_input_test.
Steinar H. Gunderson [Sun, 19 Feb 2017 15:34:15 +0000 (16:34 +0100)]
Implement mipmap generation in YCbCrInput, now that we advertise single-texture.
Steinar H. Gunderson [Sun, 19 Feb 2017 10:02:09 +0000 (11:02 +0100)]
Loosen up some restrictions on YCbCrInput if we have interleaved mode.
Steinar H. Gunderson [Tue, 14 Feb 2017 21:26:28 +0000 (22:26 +0100)]
Add support for 10- and 12-bit planar Y'CbCr inputs.
This is mostly for completeness; at least for 10-bit, 10:10:10:2
should be a faster format. However, it's nice to allow direct
subsampled inputs _somehow_.
Steinar H. Gunderson [Tue, 14 Feb 2017 20:34:27 +0000 (21:34 +0100)]
Some minor comment fixes in ycbcr.h.
Steinar H. Gunderson [Tue, 14 Feb 2017 17:50:07 +0000 (18:50 +0100)]
Add input support for packed 10-bit Y'CbCr.
Steinar H. Gunderson [Mon, 13 Feb 2017 23:18:59 +0000 (00:18 +0100)]
Support interleaved (chunky) 4:4:4 in YCbCrInput.
Steinar H. Gunderson [Mon, 13 Feb 2017 23:10:10 +0000 (00:10 +0100)]
Fix some test breakage.
Steinar H. Gunderson [Sun, 12 Feb 2017 23:55:14 +0000 (00:55 +0100)]
Support 10- and 12-bit Y'CbCr output.
We don't have any input support yet; the constants are put in place,
but we also need some work on supporting (semi-)adequate input formats.
Steinar H. Gunderson [Sat, 11 Feb 2017 21:13:02 +0000 (22:13 +0100)]
Allow adjusting the output Y'CbCr coefficients after finalize.
Primarily useful for Nageru, which may have to switch output modes runtime.
Pretty much the same speed (just a single extra branch on a boolean uniform),
as constants and uniforms are typically the same speed and we're generally
ALU-bound.
Steinar H. Gunderson [Sat, 5 Nov 2016 10:45:46 +0000 (11:45 +0100)]
Release Movit 1.4.0.
Steinar H. Gunderson [Sat, 5 Nov 2016 10:41:46 +0000 (11:41 +0100)]
Fix a typo.
Steinar H. Gunderson [Sat, 5 Nov 2016 10:32:56 +0000 (11:32 +0100)]
Fix an issue where a (cached) shader program could be used from multiple
threads at a time.
This isn't allowed, since uniforms belong to the program, not to the
context. Found by running Helgrind over Nageru.
Steinar H. Gunderson [Tue, 26 Jul 2016 13:30:56 +0000 (15:30 +0200)]
Make the error printed on check_error() slightly friendlier: Include the enum if possible, and print it to stderr instead of stdout.
Steinar H. Gunderson [Thu, 21 Jul 2016 22:40:50 +0000 (00:40 +0200)]
Be more defensive about width/height/pitch given to FlatInput and YCbCrInput.
Steinar H. Gunderson [Fri, 1 Apr 2016 21:51:28 +0000 (23:51 +0200)]
Remove a very old and outdated comment.
Steinar H. Gunderson [Fri, 1 Apr 2016 21:47:30 +0000 (23:47 +0200)]
Add some clarifying comments about the intermediate formats.
Steinar H. Gunderson [Tue, 1 Mar 2016 00:00:51 +0000 (01:00 +0100)]
Fix some comment formatting.
Steinar H. Gunderson [Mon, 29 Feb 2016 23:59:37 +0000 (00:59 +0100)]
Rework PaddingEffect alpha handling, which also fixes a long-standing assertion failure.
Steinar H. Gunderson [Sun, 28 Feb 2016 00:53:55 +0000 (01:53 +0100)]
Allow storing values in intermediate framebuffers as sqrt(x).
Together with GL_RGB10_A2, this would seem to be an even better tradeoff for
many chains than GL_SRGB8_ALPHA8 is, as long as you don't need intermediate
alpha. (We verify its accuracy with a unit test.)
This changes the API for specifying intermediate framebuffers, but that API
was never in a release, so it should be fine.
Also document a rather obscure problem where, if you can actually hold on to
non-linear values across a bounce buffer, you don't really want to store them
in sRGB encoding. (The square-root version actually avoids this problem.
I guess we could snoop on the type and do a similar thing if we see it's an
GL_SRGB* encoding, but it seems so obscure that we can ignore it for now.)
Steinar H. Gunderson [Sun, 28 Feb 2016 00:46:15 +0000 (01:46 +0100)]
Hard-assert on something that has bitten me too many times now.
Steinar H. Gunderson [Sun, 28 Feb 2016 00:26:47 +0000 (01:26 +0100)]
Fix a typo.
Steinar H. Gunderson [Sat, 27 Feb 2016 23:37:01 +0000 (00:37 +0100)]
Add support for 10-bit RGB framebuffers.
Steinar H. Gunderson [Sat, 27 Feb 2016 23:28:31 +0000 (00:28 +0100)]
Add some sRGB conversion functions to test_util.{h,cpp}.
Steinar H. Gunderson [Sat, 27 Feb 2016 23:24:04 +0000 (00:24 +0100)]
Bump version after new format support.
Steinar H. Gunderson [Wed, 24 Feb 2016 22:18:41 +0000 (23:18 +0100)]
Add support for some of the more esoteric minifloat formats to ResourcePool.
Steinar H. Gunderson [Wed, 24 Feb 2016 00:32:49 +0000 (01:32 +0100)]
Do not send NULL to glTexSubImage2D if there is no input data set; it is illegal, and NVIDIA's drivers crash on it.
Steinar H. Gunderson [Tue, 23 Feb 2016 21:48:26 +0000 (22:48 +0100)]
Merge branch '1.3.x-release'
Steinar H. Gunderson [Tue, 23 Feb 2016 21:47:05 +0000 (22:47 +0100)]
Release Movit 1.3.2. (From a branch, since I do not want to break ABI compatibility at this point.)