Alessio Bazzica b81ab995a2 RNN VAD: Optimize GRU (recurrent) weights optimized layout
This CL adds the GRU weights memory layout optimization with which it
will be easier to add SSE2 code in a follow up CL. The new memory
layout also improves the performance of the unoptimized code.

This CL also includes a bug fix in the GRU layer input validation.
It was a silent bug since the GRU layer of the RNN VAD has the same
input and output size. This was caught by changing memory layout of
the recurrent weights. The unit test has been adapted by removing the
unused recurrent weights (the expected result does not change).

Bug: webrtc:10480
Change-Id: Ia1551abde4cb24aa7e109c4447e0fffe7c839077
Reviewed-on: https://webrtc-review.googlesource.com/c/src/+/142177
Commit-Queue: Alessio Bazzica <alessiob@webrtc.org>
Reviewed-by: Gustaf Ullberg <gustaf@webrtc.org>
Cr-Commit-Position: refs/heads/master@{#29717}
2019-11-06 21:51:07 +00:00
..
2019-07-08 13:45:15 +00:00
2018-12-10 14:47:29 +00:00
2019-07-08 13:45:15 +00:00
2019-02-20 16:02:59 +00:00
2019-05-10 09:00:54 +00:00