ref: e83d99d7b8e009fd847ff91319f57abd5f7f96eb
parent: 0207f17144f213a52512cfd8287e26946e30d7ad
author: Johann <johannkoenig@google.com>
date: Thu Aug 10 11:02:22 EDT 2017
quantize fp: neon implementation About 4x faster when values are below the dequant threshold and 10x faster if everything needs to be calculated. Both numbers would improve if the division for dqcoeff could be simplified. BUG=webm:1426 Change-Id: I8da67c1f3fcb4abed8751990c1afe00bc841f4b2