commit 0fa5e6dda7e9e76d7ca5f77777c35374c768f28c
author Cathal Corbett <cathal.corbett@arm.com> Fri Jan 21 16:55:13 2022 +0000
committer Cathal Corbett <cathal.corbett@arm.com> Mon Jan 24 18:10:44 2022 +0000
tree fe4cdfe345398429328be5e5485cea5d3a0073be
parent e02562b0957b4c14739f608513d3c03050c19369

IVGCVSW-6269 Add support of Unidirectional Sequence Lstm fp32/fp16 to Android

  * Unidirectional Sequence Lstm is supported in android-nn-driver.
  * CTS and VTS pass for Unidirectional Sequence Lstm if there are
    any without weights as inputs. If that isn't the case use the
    tests implemented in the android driver for LSTM.

Signed-off-by: Cathal Corbett <cathal.corbett@arm.com>
Change-Id: Ie3a237b67f5101c4f9a2c7bea796e9c674bedba1

NnapiSupport.txt

diff --git a/NnapiSupport.txt b/NnapiSupport.txt
index 886e37b..e1b2321 100644
--- a/NnapiSupport.txt
+++ b/NnapiSupport.txt
@@ -87,6 +87,7 @@
 TANH                         (FLOAT32, FLOAT16, QUANT8_ASYMM, QUANT8_ASYMM_SIGNED)
 TRANSPOSE                    (FLOAT32, QUANT8_ASYMM, QUANT8_ASYMM_SIGNED)
 TRANSPOSE_CONV_2D            (FLOAT32, QUANT8_ASYMM, QUANT8_ASYMM_SIGNED)
+UNIDIRECTIONAL_SEQUENCE_LSTM (FLOAT32, FLOAT16)
 
 Where operations are not supported by the ArmNN Android NN Driver, the driver indicates this to the framework
 appropriately and the framework implements those operations using a CPU implementation.