Skip to content
Commit b6c69d27 authored by Max Bergfelt's avatar Max Bergfelt
Browse files

MLBEDSW-10828: Align int16 quantized scale to reference 



Changed the calculation of the scale in the QuantizedScale function to bit-exactly match the reference, in which the scale is calculated in two steps for int16 instead of one.

Change-Id: I1f72a58b3b3b7abb93ff1a4096e7be9897bd2879
Signed-off-by: Max Bergfelt's avatarMax Bergfelt <max.bergfelt@arm.com>
parent c410198c
Pipeline #28179 passed with stages
in 11 minutes and 31 seconds
Hide whitespace changes
Inline Side-by-side
0% or .
You are about to add 0 people to the discussion. Proceed with caution.
Finish editing this message first!
Please register or to comment