Remove usage of valid window region in NHWC CPU kernels - Part1

Replace all calculate_max_window(ValidRegion, ...) with
calculate_max_window(TensorShape, ...) in CPU kernels

Resolves COMPMID-4152 (1/2)

Change-Id: I7403ea6b24b9e7889890839142a06439d6c8a499
Signed-off-by: SiCongLi <sicong.li@arm.com>
Reviewed-on: https://review.mlplatform.org/c/ml/ComputeLibrary/+/5202
Reviewed-by: Georgios Pinitas <georgios.pinitas@arm.com>
Tested-by: Arm Jenkins <bsgcomp@arm.com>
Comments-Addressed: Arm Jenkins <bsgcomp@arm.com>

1 files changed, 2 insertions, 4 deletions

diff --git a/src/core/cpu/kernels/CpuElementwiseUnaryKernel.cpp b/src/core/cpu/kernels/CpuElementwiseUnaryKernel.cpp
index d2681bb060..2b5c11f8e1 100644
--- a/src/core/cpu/kernels/CpuElementwiseUnaryKernel.cpp
+++ b/src/core/cpu/kernels/CpuElementwiseUnaryKernel.cpp
@@ -113,14 +113,12 @@ void CpuElementwiseUnaryKernel::configure(ElementWiseUnary op, const ITensorInfo
     ARM_COMPUTE_ERROR_THROW_ON(validate(op, input, output));
 
     // Configure kernel window
-    const std::pair<TensorShape, ValidRegion> broadcast_pair = ITensorInfo::broadcast_shape_and_valid_region(input);
-    const TensorShape &out_shape    = broadcast_pair.first;
-    const ValidRegion &valid_region = broadcast_pair.second;
+    const TensorShape &out_shape = TensorShape::broadcast_shape(input.tensor_shape());
 
     // Auto initialize output if not initialized
     auto_init_if_empty(output, out_shape, 1, input.data_type());
 
-    Window win = calculate_max_window(valid_region);
+    Window win = calculate_max_window(out_shape);
 
     _op = op;