- 22 Sep, 2016 2 commits
-
-
Anton Khirnov authored
The x86 version processes 16 floats per iteration, so len must be a multiple of 16.
-
Anton Khirnov authored
This will make the x86 asm simpler. ARM conversion by Martin Storsjö <martin@martin.st> and Janne Grunau <janne-libav@jannau.net>
-
- 22 Jun, 2014 1 commit
-
-
Diego Biurrun authored
-
