George Steed dff7bad43d [AArch64] Use full Neon vectors in ARGB4444ToARGBRow_NEON
The existing Neon code narrows the input 16-bit packed data to 8-bit
elements and separates the color channels, causing us to only process
half a Neon vector per instruction for the channel widening from 4-bit
color data to 8-bits.

We can note that the processing being done is identical for all color
channels and therefore we can keep them partially interleaved during the
widening step. This allows us to use full Neon vectors for the whole
loop body.

Reductions in runtimes observed for ARGB4444ToARGBRow_NEON:

 Cortex-A55: -30.7%
Cortex-A510: -44.3%
 Cortex-A76: -51.6%
  Cortex-X2: -54.2%

Bug: libyuv:976
Change-Id: I9d9cda7e16eb07619c6d7f1de2e6b8c0fb6d64cf
Reviewed-on: https://chromium-review.googlesource.com/c/libyuv/libyuv/+/5594389
Reviewed-by: Frank Barchard <fbarchard@chromium.org>
2024-06-03 22:52:33 +00:00
build_overrides Define enable_safe_libcxx in build_overrides/build.gni. 2023-05-03 06:08:40 +00:00
docs [docs] Add documentation on AArch64 SME for feature detection 2024-06-03 22:39:03 +00:00
include [AArch64] Add Neon impls for I{210,410}ToAR30Row_NEON 2024-06-03 22:46:12 +00:00
infra/config infra: Move libyuv ci/try jobs from Ubuntu-18.04 to Ubuntu-22.04 2024-05-21 15:55:24 +00:00
riscv_script [RISC-V] Support CMake build with custom compiler flags 2023-07-25 09:21:59 +00:00
source [AArch64] Use full Neon vectors in ARGB4444ToARGBRow_NEON 2024-06-03 22:52:33 +00:00
tools_libyuv Do not roll the Fuchsia SDK. 2023-07-03 09:18:00 +00:00
unit_test Remove unneeded #ifdef HAVE_JPEG code 2024-05-09 23:02:18 +00:00
util [AArch64] Enable detection of additional architecture features 2024-04-05 17:48:22 +00:00
.clang-format clang-format libyuv 2016-11-07 17:37:23 -08:00
.gitignore DetilePlane and unittest for NEON 2022-01-31 20:05:55 +00:00
.gn Roll chromium_revision 829c6df33d..7d683aeda8 (945687:1050091) 2022-09-22 14:56:57 +00:00
.vpython remove swarming_client 2021-09-09 07:11:45 +00:00
.vpython3 Update vpython3 requests 2023-06-01 19:06:40 +00:00
Android.bp Split scale_test and scale_plane_test to allow building on small devices 2023-12-09 18:39:41 +00:00
Android.mk Split scale_test and scale_plane_test to allow building on small devices 2023-12-09 18:39:41 +00:00
AUTHORS [DEPS] Remove cleanup_links pre_deps_hooks 2024-04-08 15:47:48 +00:00
BUILD.gn [AArch64] Add :libyuv_sve library in preparation for SVE kernels 2024-04-09 03:10:01 +00:00
CM_linux_packages.cmake Reduce cmake verbosity and update min version 2022-08-03 06:59:54 +00:00
CMakeLists.txt CMake: Use CMAKE_SOURCE_DIR in GTEST_SRC_DIR 2024-04-11 09:09:46 +00:00
codereview.settings [infra] remove no longer supported git cl upload setting. 2021-04-28 12:47:52 +00:00
DEPS [DEPS] Remove cleanup_links pre_deps_hooks 2024-04-08 15:47:48 +00:00
DIR_METADATA Move metadata in OWNERS files to DIR_METADATA files 2021-02-09 19:34:43 +00:00
download_vs_toolchain.py Update gclient instructions + environment 2022-02-24 15:19:23 +00:00
libyuv.gni [AArch64] Add :libyuv_sve library in preparation for SVE kernels 2024-04-09 03:10:01 +00:00
libyuv.gyp Add libyuv.gyp build files 2022-03-21 23:48:16 +00:00
libyuv.gypi Fix missing headers in GN/GYP build files 2024-04-01 09:19:24 +00:00
LICENSE Update Copyright notice to follow new chromium conventions. 2012-08-08 19:04:24 +00:00
linux.mk Split convert_test and convert_argb_test to allow building on small systems that run out of memory compiling unittests. 2023-12-08 13:39:56 +00:00
OWNERS add jansson@google.com to infra owners to cover when Mirko is OOO 2022-10-28 09:46:02 +00:00
PATENTS LibYuv: Adding PATENT and LICENSE files 2011-10-25 16:15:49 +00:00
PRESUBMIT.py Update PRESUBMIT, cleanup_links and autoroller to py3 2022-02-24 13:34:14 +00:00
public.mk use unix line endings 2018-06-20 23:19:59 +00:00
pylintrc Use DEPS for all dependencies + add PRESUBMIT.py 2017-02-03 11:36:53 +00:00
README.chromium Fix environment variable LIBYUV_CPU_INFO for unittests 2024-04-20 17:41:56 +00:00
README.md Add RAWToARGBRow_RVV,RAWToRGBARow_RVV,RAWToRGB24Row_RVV 2023-04-07 18:45:08 +00:00
winarm.mk NV12 Copy, include scale_uv.h 2020-12-08 18:54:16 +00:00

libyuv is an open source project that includes YUV scaling and conversion functionality.

  • Scale YUV to prepare content for compression, with point, bilinear or box filter.
  • Convert to YUV from webcam formats for compression.
  • Convert to RGB formats for rendering/effects.
  • Rotate by 90/180/270 degrees to adjust for mobile devices in portrait mode.
  • Optimized for SSSE3/AVX2 on x86/x64.
  • Optimized for Neon on Arm.
  • Optimized for MSA on Mips.
  • Optimized for RVV on RISC-V.

Development

See Getting started for instructions on how to get started developing.

You can also browse the docs directory for more documentation.