tree f9ea15d422c9f76d1aace78b5be10759def58323
parent ac1b09ba78894d7391ae186cb3876cf390f1d9be
author Jonathan Wright <jonathan.wright@arm.com> 1654189762 +0100
committer James Zern <jzern@google.com> 1663651106 +0000

Optimize av1_convolve_2d_sr_neon using SDOT instruction

Add an alternative AArch64 implementation of
av1_convolve_2d_sr_horiz_neon - the horizontal portion of
av1_convolve_2d_sr_neon - using the Armv8.4-A SDOT (signed dot-
product) instruction.

The existing MLA-based implementation of is retained and used on
target CPUs that do not implement the SDOT instruction (or CPUs
executing in AArch32 mode.) The availability of the SDOT instruction
is indicated by the feature macro __ARM_FEATURE_DOTPROD.

Change-Id: Ib22663122bc19f000300f088ae5691f9bcf977d1