COMPMID-2069: Rework CL ML layers to run exclusively on CL.

Change-Id: If6cbf7a2e013d264e5d7f7cb54143ce32ba2687b
Signed-off-by: Georgios Pinitas <georgios.pinitas@arm.com>
Reviewed-on: https://review.mlplatform.org/c/934
Comments-Addressed: Arm Jenkins <bsgcomp@arm.com>
Reviewed-by: Isabella Gottardi <isabella.gottardi@arm.com>
Reviewed-by: Gian Marco Iodice <gianmarco.iodice@arm.com>
Tested-by: Arm Jenkins <bsgcomp@arm.com>
diff --git a/arm_compute/runtime/CL/functions/CLLSTMLayer.h b/arm_compute/runtime/CL/functions/CLLSTMLayer.h
index a804a4a..8bd47cb 100644
--- a/arm_compute/runtime/CL/functions/CLLSTMLayer.h
+++ b/arm_compute/runtime/CL/functions/CLLSTMLayer.h
@@ -29,6 +29,7 @@
 #include "arm_compute/core/CL/kernels/CLActivationLayerKernel.h"
 #include "arm_compute/core/CL/kernels/CLCopyKernel.h"
 #include "arm_compute/core/CL/kernels/CLElementwiseOperationKernel.h"
+#include "arm_compute/core/CL/kernels/CLMemsetKernel.h"
 #include "arm_compute/core/CL/kernels/CLPixelWiseMultiplicationKernel.h"
 #include "arm_compute/core/CL/kernels/CLWidthConcatenate2TensorsKernel.h"
 #include "arm_compute/core/Types.h"
@@ -188,6 +189,7 @@
     CLWidthConcatenate2TensorsKernel     _concat_weights_forget_gate;
     CLWidthConcatenate2TensorsKernel     _concat_weights_input_gate;
     CLWidthConcatenate2TensorsKernel     _concat_weights_output;
+    CLMemsetKernel                       _ones_memset_kernel;
     CLTensor                             _input_gate_out1;
     CLTensor                             _input_gate_out2;
     CLTensor                             _input_gate_out3;