KonstantinSeurer/mesa: Mesa3D Graphics Library (Bleeding edge ray tracing branches)

Mesa3D Graphics Library (Bleeding edge ray tracing branches)

Go to file

Eric Anholt d845dca0f5 nir: Make algebraic backtrack and reprocess after a replacement. The algebraic pass was exhibiting O(n^2) behavior in dEQP-GLES2.functional.uniform_api.random.3 and dEQP-GLES31.functional.ubo.random.all_per_block_buffers.13 (along with other code-generated tests, and likely real-world loop-unroll cases). In the process of using fmul(b2f(x), b2f(x)) -> b2f(iand(x, y)) to transform: result = b2f(a == b); result = b2f(c == d); ... result = b2f(z == w); -> temp = (a == b) temp = temp && (c == d) ... temp = temp && (z == w) result = b2f(temp); nir_opt_algebraic, proceeding bottom-to-top, would match and convert the top-most fmul(b2f(), b2f()) case each time, leaving the new b2f to be matched by the next fmul down on the next time algebraic got run by the optimization loop. Back in 2016 in `7be8d07732` ("nir: Do opt_algebraic in reverse order."), Matt changed algebraic to go bottom-to-top so that we would match the biggest patterns first. This helped his cases, but I believe introduced this failure mode. Instead of reverting that, now that we've got the automaton, we can update the automaton's state recursively and just re-process any instructions whose state has changed (indicating that they might match new things). There's a small chance that the state will hash to the same value and miss out on this round of algebraic, but this seems to be good enough to fix dEQP. Effects with NIR_VALIDATE=0 (improvement is better with validation enabled): Intel shader-db runtime -0.954712% +/- 0.333844% (n=44/46, obvious throttling outliers removed) dEQP-GLES2.functional.uniform_api.random.3 runtime -65.3512% +/- 4.22369% (n=21, was 1.4s) dEQP-GLES31.functional.ubo.random.all_per_block_buffers.13 runtime -68.8066% +/- 6.49523% (was 4.8s) v2: Use two worklists, suggested by @cwabbott, to cut out a bunch of tricky code. Runtime of uniform_api.random.3 down -0.790299% +/- 0.244213% compred to v1. v3: Re-add the nir_instr_remove() that I accidentally dropped in v2, fixing infinite loops. Reviewed-by: Connor Abbott <cwabbott0@gmail.com>		2019-11-26 10:13:46 -08:00
.appveyor	Appveyor: Quickly fix meson build.	2019-11-14 21:45:23 +00:00
.gitlab-ci	llvmpipe: initial query buffer object support. (v2)	2019-11-25 12:37:32 +10:00
bin	meson: add windows support to symbols checks	2019-11-05 20:31:37 +00:00
build-support	…
docs	docs: add llvmpipe to ARB_query_buffer_object.	2019-11-25 12:37:58 +10:00
doxygen	…
include	vulkan: Update the XML and headers to 1.1.129	2019-11-26 02:48:42 +00:00
scons	mesa/imports: let the build system detect strtok_r()	2019-11-05 22:38:04 +00:00
src	nir: Make algebraic backtrack and reprocess after a replacement.	2019-11-26 10:13:46 -08:00
subprojects	meson: add a expat subproject	2019-09-10 20:36:47 +00:00
.dir-locals.el	…
.editorconfig	editorconfig: Fix meson style	2019-05-24 18:44:18 +00:00
.gitignore	intel/tools: Add unit tests for assembler	2019-05-07 14:33:48 -07:00
.gitlab-ci.yml	gitlab-ci/deqp: generate junit results	2019-11-22 13:48:29 -08:00
.mailmap	.mailmap: add a couple of aliases for Jakob Bornecrantz	2019-10-03 17:11:20 -04:00
.travis.yml	travis: fix scons build after deprecation warning	2019-10-29 09:25:40 +00:00
Android.common.mk	android: mesa: Revert "android: mesa: revert "Enable asm unconditionally""	2019-11-12 18:09:43 +00:00
Android.mk	android: mesa: Revert "android: mesa: revert "Enable asm unconditionally""	2019-11-12 18:09:43 +00:00
CleanSpec.mk	CleanSpec.mk: Remove HOST_OUT_release	2018-08-02 15:42:40 -06:00
README.rst	README: Drop the badges from the readme	2019-02-07 12:46:17 -06:00
REVIEWERS	REVIEWERS: add VMware reviewers	2019-10-18 16:42:40 +00:00
SConstruct	scons: Fix force_scons parsing.	2019-10-26 08:23:48 +01:00
VERSION	Bump VERSION to 20.0.0-devel	2019-10-30 14:56:02 -07:00
appveyor.yml	Appveyor: Quickly fix meson build.	2019-11-14 21:45:23 +00:00
common.py	scons: Print a deprecation warning about using scons on not windows	2019-10-24 18:33:50 +00:00
meson.build	meson: only build imgui when needed	2019-11-25 07:51:56 +00:00
meson_options.txt	util: Use ZSTD for shader cache if possible	2019-11-11 18:53:45 +00:00

README.rst

`Mesa <https://mesa3d.org>`_ - The 3D Graphics Library
======================================================


Source
------

This repository lives at https://gitlab.freedesktop.org/mesa/mesa.
Other repositories are likely forks, and code found there is not supported.


Build & install
---------------

You can find more information in our documentation (`docs/install.html
<https://mesa3d.org/install.html>`_), but the recommended way is to use
Meson (`docs/meson.html <https://mesa3d.org/meson.html>`_):

.. code-block:: sh

  $ mkdir build
  $ cd build
  $ meson ..
  $ sudo ninja install


Support
-------

Many Mesa devs hang on IRC; if you're not sure which channel is
appropriate, you should ask your question on `Freenode's #dri-devel
<irc://chat.freenode.net#dri-devel>`_, someone will redirect you if
necessary.
Remember that not everyone is in the same timezone as you, so it might
take a while before someone qualified sees your question.
To figure out who you're talking to, or which nick to ping for your
question, check out `Who's Who on IRC
<https://dri.freedesktop.org/wiki/WhosWho/>`_.

The next best option is to ask your question in an email to the
mailing lists: `mesa-dev\@lists.freedesktop.org
<https://lists.freedesktop.org/mailman/listinfo/mesa-dev>`_


Bug reports
-----------

If you think something isn't working properly, please file a bug report
(`docs/bugs.html <https://mesa3d.org/bugs.html>`_).


Contributing
------------

Contributions are welcome, and step-by-step instructions can be found in our
documentation (`docs/submittingpatches.html
<https://mesa3d.org/submittingpatches.html>`_).

Note that Mesa uses email mailing-lists for patches submission, review and
discussions.