]> git.sesse.net Git - x264/commit
projects / x264 / commit
? search:
summary | shortlog | log | commit | commitdiff | tree
(parent: 3e25eab) | patch
arm: Implement x264_mbtree_propagate_{cost, list}_neon
authorMartin Storsjö <martin@martin.st>
Thu, 3 Sep 2015 06:30:44 +0000 (09:30 +0300)
committerHenrik Gramner <henrik@gramner.com>
Sun, 11 Oct 2015 16:44:54 +0000 (18:44 +0200)
commit6f04b146875c45e6f7845a7bb5fb7fdf8e7534f1
treebe5e01a6761afdc5ba940d8e0a43033b2b22fc54tree | snapshot
parent3e25eab0b7172e3c0b067b8b6d641ce148d03db9commit | diff
arm: Implement x264_mbtree_propagate_{cost, list}_neon

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
common/arm/mc-a.S diff | blob | history
common/arm/mc-c.c diff | blob | history
Unnamed repository; edit this file 'description' to name the repository.