Find a file
Francisco Jerez 6eea9659db intel/brw/xe3+: Model trade-off between parallelism and GRF use in performance analysis.
This extends the performance analysis pass used in previous
generations to make it more useful to deal with the performance
trade-off encountered on xe3 hardware as a result of VRT.  VRT allows
the driver to request a per-thread GRF allocation different from the
128 GRFs that were typical in previous platforms, but this comes at
either a thread parallelism cost or benefit depending on the number of
GRF register blocks requested.

This makes a number of decisions more difficult for the compiler since
certain optimizations potentially trade off run-time in a thread
against the total number of threads that can run in parallel
(e.g. consider scheduling and how reordering an instruction to avoid a
stall can increase GRF use and therefore reduce thread-level
parallelism when trying to improve instruction-level parallelism).

This patch provides a simple heuristic tool to account for the
combined interaction of register pressure and other single-threaded
factors that affect performance.  This is expressed with the
redefinition of the pre-existing brw_performance::throughput estimate
as the number of invocations per cycle per EU that would be achieved
if there were enough threads to reach full load (in this sense this is
to be considered a heuristic since the penalty from VRT may be lower
than expected from this model at low EU load).

This will be used e.g. in order to decide whether to use a more
aggressive latency-minimizing mode during scheduling or a mode more
effective at minimizing register pressure (it makes sense to take the
path that will lead to the most invocations being serviced per cycle
while under load).  This also allows us to re-enable the old PS SIMD32
heuristic on xe3+, and due to this change it is able to identify cases
where the combined effect of poorer scheduling and higher GRF use of
the SIMD32 variant makes it more favorable to use SIMD16 only (see
last patch of the MR for details and numbers).

Reviewed-by: Lionel Landwerlin <lionel.g.landwerlin@intel.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/36618>
2025-09-10 02:15:56 +00:00
.ci-farms Revert "ci: disable Collabora's farm due to maintenance" 2025-09-08 16:16:52 +00:00
.ci-farms-disabled Revert "ci: disable Collabora's farm due to maintenance" 2025-09-08 16:16:52 +00:00
.github/workflows meson: remove unused osmesa option 2025-06-23 06:42:50 +00:00
.gitlab docs: update gitlab docs urls 2025-02-23 00:31:59 +01:00
.gitlab-ci ci-tron: uprev b2c to v0.9.17 2025-09-02 07:48:53 +00:00
.marge/hooks ci: pipeline_message: reset empty errors 2025-01-07 05:08:10 +00:00
android android: Only include libdrm_intel for i915 as iris do not depend on it 2025-09-04 07:53:36 +00:00
bin ci/update_traces_checksum: fix regex detecting PIGLIT_REPLAY_DEVICE_NAME in job logs 2025-09-08 13:39:39 +00:00
build-support meson: move tsan-blacklist.txt to build-support with the other build support files 2024-05-01 07:05:12 +00:00
docs util/log: Add a MESA_LOG_LEVEL environment variable 2025-09-08 21:28:10 +00:00
include freedreno/drm: Import new UABI for VM_BIND 2025-08-25 20:11:57 +00:00
licenses licenses: add missing licenses 2025-01-08 20:37:51 +00:00
src intel/brw/xe3+: Model trade-off between parallelism and GRF use in performance analysis. 2025-09-10 02:15:56 +00:00
subprojects subprojects: fix ignore exception for files under packagefiles/ 2025-08-25 15:55:53 +00:00
.clang-format meson: enable the clang-format target 2023-05-29 11:57:08 +00:00
.clang-format-ignore ci: enforce formatting for RADV & ACO 2023-06-16 19:59:52 +00:00
.clang-format-include rocket: Initial commit of a driver for Rockchip's NPU 2025-07-28 08:06:38 +02:00
.dir-locals.el
.editorconfig editorconfig: move OpenCL configuration to root 2025-08-30 22:49:08 -07:00
.git-blame-ignore-revs freedreno: Add register renaming to .git-blame-ignore-revs 2025-07-03 12:50:04 +00:00
.gitattributes gitlab: Highlight .cl as C 2023-11-02 11:37:46 +00:00
.gitignore .gitignore: Add KDevelop *.kdev4 2025-07-24 16:12:10 +00:00
.gitlab-ci.yml ci/ci-tron: uprev the job submission template 2025-08-25 12:46:54 +00:00
.graphqlrc.yml
.mailmap mailmap: Update my name 2025-09-09 16:44:38 +00:00
.mr-label-maker.yml mr-label-maker.yml: remove remaining osmesa occurrences 2025-06-23 06:42:50 +00:00
.shellcheckrc ci: move shellcheck options to .shellcheckrc 2024-10-24 22:43:03 +00:00
CODEOWNERS intel: update code owners 2025-08-31 15:38:27 +00:00
meson.build teflon/tests: Remove dependency on xtensor 2025-09-09 11:07:19 +02:00
meson.options zink: Add zink_check_requirements 2025-08-22 16:08:11 -04:00
README.rst docs: Match README installation guide with meson.rst 2024-07-27 11:53:53 +00:00
rustfmt.toml mesa: Add rustfmt.toml 2024-11-18 22:29:14 +00:00
VERSION VERSION: bump to 25.3 2025-07-16 13:50:24 +00:00

`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.rst
<https://docs.mesa3d.org/install.html>`_), but the recommended way is to use
Meson (`docs/meson.rst <https://docs.mesa3d.org/meson.html>`_):

.. code-block:: sh

  $ meson setup build
  $ ninja -C build/
  $ sudo ninja -C build/ install

Support
-------

Many Mesa devs hang on IRC; if you're not sure which channel is
appropriate, you should ask your question on `OFTC's #dri-devel
<irc://irc.oftc.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.rst <https://docs.mesa3d.org/bugs.html>`_).


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

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

Note that Mesa uses gitlab for patches submission, review and discussions.