COMPMID-2707: add keep_dims parameter to Reduction Operation

The added parameter is used to decide whether or not to keep
the target dimension of reduction operation. ArgMinMax operations
will always remove the reduced dimension. Following things
are updated to support the parameter.

- [CL/NEON] functions and reference kernel
- [CL/NEON] ArgMinMax function to use ReductionOperation function
- [CL/NEON] validation test suite for Reduction and ArgMinMax operations
  to validate the added parameter
- ReductionOperationFixture is modified NOT to pre-populate output
  tensor and now relies on underlying kernel/function.
- Adjust CL validation test suite for Reduction operation to remove
  excessive test cases with axis values beyond input tensor's
  dimension.

Change-Id: I3e24d276ed469a4201f323001708f0c525f11c4f
Signed-off-by: Sang-Hoon Park <sang-hoon.park@arm.com>
Reviewed-on: https://review.mlplatform.org/c/2167
Comments-Addressed: Arm Jenkins <bsgcomp@arm.com>
Tested-by: Arm Jenkins <bsgcomp@arm.com>
Reviewed-by: Michele Di Giorgio <michele.digiorgio@arm.com>
Reviewed-by: Georgios Pinitas <georgios.pinitas@arm.com>

1 files changed, 13 insertions, 4 deletions

diff --git a/arm_compute/core/utils/misc/ShapeCalculator.h b/arm_compute/core/utils/misc/ShapeCalculator.h
index c4c360842f..080d63f60d 100644
--- a/arm_compute/core/utils/misc/ShapeCalculator.h
+++ b/arm_compute/core/utils/misc/ShapeCalculator.h
@@ -1179,15 +1179,24 @@ inline TensorShape compute_tiled_shape(const TensorShape &input_shape, const Mul
 
 /** Calculate the reduced shape of a tensor given an axis
  *
- * @param[in] input Input tensor info
- * @param[in] axis  Axis on which to perform reduction
+ * @param[in] input     Input tensor info
+ * @param[in] axis      Axis on which to perform reduction
+ * @param[in] keep_dims (Optional) Whether to keep the dimension after reduction operation. Defaults to true.
  *
  * @return the calculated shape
  */
-inline TensorShape compute_reduced_shape(const TensorShape &input, unsigned int axis)
+inline TensorShape compute_reduced_shape(const TensorShape &input, unsigned int axis, bool keep_dims = true)
 {
     TensorShape output_shape{ input };
-    output_shape.set(axis, 1);
+
+    if(!keep_dims)
+    {
+        output_shape.remove_dimension(axis);
+    }
+    else
+    {
+        output_shape.set(axis, 1);
+    }
 
     return output_shape;
 }