| commit | 4fe9de3b0f17f4d6146a3d541daf869742629c5d | [log] [tgz] |
|---|---|---|
| author | Linfeng Zhang <linfengz@google.com> | Wed Jan 25 09:45:48 2017 -0800 |
| committer | Jean-Marc Valin <jmvalin@jmvalin.ca> | Tue Jun 06 17:12:20 2017 -0400 |
| tree | 5f75241d09846e089cd8d015a3458e02cc4cd372 | |
| parent | 4d4ed208b1dfd8cdbb1df89382fbaa1815972e55 [diff] |
Optimize floating-point celt_inner_prod() and dual_inner_prod() for ARM NEON The floating-point optimizations are not bit exact with C functions, because of the different orders of floating-point operations. But they are bit exact with the simulation C functions which simulate the floating operations in the optimizations. Change-Id: I149fda5b602fd5712b16fc8983df3c6c0c9e76ad Signed-off-by: Jean-Marc Valin <jmvalin@jmvalin.ca>