COMPMID-1566: Add broadcast to CLArithmeticSubtraction

Change-Id: I05d21f9a92013ecfd1128d12cf1561cfd6e5c5e9
Reviewed-on: https://eu-gerrit-1.euhpc.arm.com/147983
Tested-by: bsgcomp <bsgcomp@arm.com>
Reviewed-by: Anthony Barbier <anthony.barbier@arm.com>
diff --git a/arm_compute/runtime/CL/functions/CLArithmeticSubtraction.h b/arm_compute/runtime/CL/functions/CLArithmeticSubtraction.h
index b969080..2940044 100644
--- a/arm_compute/runtime/CL/functions/CLArithmeticSubtraction.h
+++ b/arm_compute/runtime/CL/functions/CLArithmeticSubtraction.h
@@ -36,6 +36,10 @@
  *
  * @note The tensor data type for the inputs must be U8/S16/F16/F32.
  * @note The function performs an arithmetic subtraction between two tensors.
+ *
+ *  This function calls the following kernels:
+ * -# @ref CLFillBorderKernel (In case of broadcasting, in the input being broadcasted)
+ * -# @ref CLArithmeticSubtractionKernel
  */
 class CLArithmeticSubtraction : public ICLSimpleFunction
 {
@@ -47,7 +51,7 @@
      * @param[out] output Output tensor. Data types supported: U8 (Only if both inputs are U8), S16/F16/F32.
      * @param[in]  policy Policy to use to handle overflow.
      */
-    void configure(const ICLTensor *input1, const ICLTensor *input2, ICLTensor *output, ConvertPolicy policy);
+    void configure(ICLTensor *input1, ICLTensor *input2, ICLTensor *output, ConvertPolicy policy);
     /** Static function to check if given info will lead to a valid configuration of @ref CLArithmeticSubtraction
      *
      * @param[in] input1 First tensor input info. Data types supported: U8/S16/F16/F32.
diff --git a/arm_compute/runtime/NEON/functions/NEArithmeticSubtraction.h b/arm_compute/runtime/NEON/functions/NEArithmeticSubtraction.h
index 9b460c1..541756c 100644
--- a/arm_compute/runtime/NEON/functions/NEArithmeticSubtraction.h
+++ b/arm_compute/runtime/NEON/functions/NEArithmeticSubtraction.h
@@ -31,7 +31,15 @@
 {
 class ITensor;
 
-/** Basic function to run @ref NEArithmeticSubtractionKernel */
+/** Basic function to run @ref NEArithmeticSubtractionKernel
+ *
+ * @note The tensor data type for the inputs must be U8/S16/F16/F32.
+ * @note The function performs an arithmetic subtraction between two tensors.
+ *
+ *  This function calls the following kernels:
+ * -# @ref NEFillBorderKernel (In case of broadcasting, in the input being broadcasted)
+ * -# @ref NEArithmeticSubtractionKernel
+ */
 class NEArithmeticSubtraction : public INESimpleFunction
 {
 public:
@@ -42,7 +50,7 @@
      * @param[out] output Output tensor. Data types supported: U8/S16/F16/F32
      * @param[in]  policy Policy to use to handle overflow.
      */
-    void configure(const ITensor *input1, const ITensor *input2, ITensor *output, ConvertPolicy policy);
+    void configure(ITensor *input1, ITensor *input2, ITensor *output, ConvertPolicy policy);
     /** Static function to check if given info will lead to a valid configuration of @ref NEArithmeticSubtraction
      *
      * @param[in] input1 First tensor input. Data types supported: U8/S16/F16/F32