[x264-devel] [PATCH 2/2] arm: Implement x264_mbtree_propagate_{cost, list}_neon

[Henrik Gramner]

On Thu, Sep 3, 2015 at 8:30 AM, Martin Storsjö <martin at martin.st> wrote:
> The cost function could be simplified to avoid having to clobber
> q4/q5, but this requires reordering instructions which increase
> the total runtime.
>
> checkasm timing       Cortex-A7      A8      A9
> mbtree_propagate_cost_c      63702   155835  62829
> mbtree_propagate_cost_neon   17199   10454   11106
>
> mbtree_propagate_list_c      104203  108949  84532
> mbtree_propagate_list_neon   82035   78348   60410

Applied.