Add batched indices support to Scatter GPU Implementation

Resolves: [COMPMID-6897]
Signed-off-by: Mohammed Suhail Munshi <MohammedSuhail.Munshi@arm.com>
Change-Id: I70b1c3c5f0de8484fcb6c3b0cc0d0d8c059b0f58
Reviewed-on: https://review.mlplatform.org/c/ml/ComputeLibrary/+/11525
Comments-Addressed: Arm Jenkins <bsgcomp@arm.com>
Reviewed-by: Gunes Bayir <gunes.bayir@arm.com>
Tested-by: Arm Jenkins <bsgcomp@arm.com>
Benchmark: Arm Jenkins <bsgcomp@arm.com>

1 files changed, 1 insertions, 0 deletions

diff --git a/tests/validation/reference/ScatterLayer.cpp b/tests/validation/reference/ScatterLayer.cpp
index c9e6035e14..55c48a9002 100644
--- a/tests/validation/reference/ScatterLayer.cpp
+++ b/tests/validation/reference/ScatterLayer.cpp
@@ -63,6 +63,7 @@ T reduce_op(const T &current,const T &update,const ScatterFunction func)
 }
 
 template float reduce_op(const float &current,const float &update,const ScatterFunction func);
+template half reduce_op(const half &current,const half &update,const ScatterFunction func);
 }
 
 // NOTE: This function expects collapsed tensors as input.