mirror of
https://gitlab.freedesktop.org/mesa/mesa.git
synced 2026-01-14 11:50:17 +01:00
read-only mirror of https://gitlab.freedesktop.org/mesa/mesa
f48aff4943
Add ARM NEON implementation of convert_ubyte_rgba_to_bgra() using architecture-specific instructions for efficient channel shuffling. ARM64 uses vqtbl1q_u8 for table-based shuffling, while ARM32 uses vrev32q_u8 + vextq_u8 for byte reversal. The implementation processes multiple pixels per iteration with proper handling of non-aligned widths via a scalar tail path. Performance improvements across three ARM platforms: ARM32 Cortex-A9: - 64x64: 3.1x faster (0.85 GB/s → 2.63 GB/s) - 1920x1080: 1.06x faster (0.83 GB/s → 0.88 GB/s) - 3840x2160: 1.07x faster (0.85 GB/s → 0.90 GB/s) ARM64 Cortex-A53: - 64x64: 3.8x faster (2.30 GB/s → 8.78 GB/s) - 1920x1080: 1.4x faster (2.85 GB/s → 3.98 GB/s) - 3840x2160: 1.4x faster (2.89 GB/s → 4.12 GB/s) Apple M2: - 64x64: 3.3x faster (21.1 GB/s → 69.7 GB/s) - 1920x1080: 1.7x faster (58.2 GB/s → 96.7 GB/s) - 3840x2160: 1.3x faster (53.5 GB/s → 68.8 GB/s) The optimization provides consistent speedups across image sizes and ARM variants, with larger gains on smaller images due to better cache utilization. On large images, performance becomes memory bandwidth-limited across all platforms. The NEON path is enabled for both AARCH64 and ARM when NEON is available (!__SOFTFP__), falling back to the existing scalar implementation on other architectures or when explicitly disabled via NO_FORMAT_ASM. Signed-off-by: Christian Gmeiner <cgmeiner@igalia.com> |
||
|---|---|---|
| .ci-farms | ||
| .ci-farms-disabled | ||
| .github/workflows | ||
| .gitlab | ||
| .gitlab-ci | ||
| .marge/hooks | ||
| android | ||
| bin | ||
| build-support | ||
| docs | ||
| include | ||
| licenses | ||
| src | ||
| subprojects | ||
| .clang-format | ||
| .clang-format-ignore | ||
| .clang-format-include | ||
| .dir-locals.el | ||
| .editorconfig | ||
| .git-blame-ignore-revs | ||
| .gitattributes | ||
| .gitignore | ||
| .gitlab-ci.yml | ||
| .graphqlrc.yml | ||
| .mailmap | ||
| .mr-label-maker.yml | ||
| .shellcheckrc | ||
| CODEOWNERS | ||
| meson.build | ||
| meson.options | ||
| README.rst | ||
| rustfmt.toml | ||
| VERSION | ||
`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.