| commit | be5de19db32f6191f2533d0fa69166e89ea60915 | [log] [tgz] |
|---|---|---|
| author | George Steed <george.steed@arm.com> | Wed May 15 21:20:11 2024 +0100 |
| committer | Frank Barchard <fbarchard@chromium.org> | Fri Jul 19 19:51:17 2024 +0000 |
| tree | ee7314665ddf0a825fc6ce65b847c91b893a60f8 | |
| parent | 42d33341d31687acd1c18e446b8d8fd68ea5cbc1 [diff] |
[AArch64] Unroll ScaleRowUp2_Linear_NEON On little cores with limited out-of-order capability this gives a good improvement. Reduction in runtimes observed compared to the existing Neon implementation: Cortex-A55: -21.3% Cortex-A520: -33.6% Cortex-A76: +1.1% Cortex-A715: =0.0% Cortex-A720: =0.0% Cortex-X1: +10.4% (!) Cortex-X2: -5.3% Cortex-X3: -4.3% Cortex-X4: -9.9% Bug: b/42280945 Change-Id: I45b3510f13c05b19d61052e2f8e447199dbd0551 Reviewed-on: https://chromium-review.googlesource.com/c/libyuv/libyuv/+/5725169 Reviewed-by: Frank Barchard <fbarchard@chromium.org>
libyuv is an open source project that includes YUV scaling and conversion functionality.
See Getting started for instructions on how to get started developing.
You can also browse the docs directory for more documentation.