COMPMID-3480: Perform in-place computations in NEArithmeticAdditionKernel

Change-Id: I0089657dd95d7c7b8592984def8e8de1d7e6d085
Signed-off-by: Michele Di Giorgio <michele.digiorgio@arm.com>
Reviewed-on: https://review.mlplatform.org/c/ml/ComputeLibrary/+/3308
Tested-by: Arm Jenkins <bsgcomp@arm.com>
Reviewed-by: Georgios Pinitas <georgios.pinitas@arm.com>
Comments-Addressed: Arm Jenkins <bsgcomp@arm.com>

2 files changed, 18 insertions, 18 deletions

diff --git a/arm_compute/core/NEON/kernels/NEArithmeticAdditionKernel.h b/arm_compute/core/NEON/kernels/NEArithmeticAdditionKernel.h
index bff34dfda2..50c90b521a 100644
--- a/arm_compute/core/NEON/kernels/NEArithmeticAdditionKernel.h
+++ b/arm_compute/core/NEON/kernels/NEArithmeticAdditionKernel.h
@@ -68,12 +68,12 @@ public:
      *   - (QASYMM8_SIGNED,QASYMM8_SIGNED) -> QASYMM8_SIGNED
      *   - (QSYMM16,QSYMM16) -> QSYMM16
      *
-     * @param[in]  input1 First input tensor. Data types supported: U8/QASYMM8/QASYMM8_SIGNED/S16/QSYMM16/F16/S32/F32
-     * @param[in]  input2 Second input tensor. Data types supported: U8/QASYMM8/QASYMM8_SIGNED/S16/QSYMM16/F16/S32/F32
-     * @param[out] output The output tensor. Data types supported: U8/QASYMM8/QASYMM8_SIGNED/S16/QSYMM16/F16/S32/F32.
-     * @param[in]  policy Overflow policy.
+     * @param[in, out] input1 First input tensor. Data types supported: U8/QASYMM8/QASYMM8_SIGNED/S16/QSYMM16/F16/S32/F32
+     * @param[in]      input2 Second input tensor. Data types supported: U8/QASYMM8/QASYMM8_SIGNED/S16/QSYMM16/F16/S32/F32
+     * @param[out]     output (Optional) The output tensor. Can be nullptr. Data types supported: U8/QASYMM8/QASYMM8_SIGNED/S16/QSYMM16/F16/S32/F32.
+     * @param[in]      policy Overflow policy.
      */
-    void configure(const ITensor *input1, const ITensor *input2, ITensor *output, ConvertPolicy policy);
+    void configure(ITensor *input1, const ITensor *input2, ITensor *output, ConvertPolicy policy);
     /** Static function to check if given info will lead to a valid configuration of @ref NEArithmeticAdditionKernel
      *
      * @param[in] input1 First input tensor info. Data types supported: U8/QASYMM8/QASYMM8_SIGNED/S16/QSYMM16/F16/S32/F32
@@ -91,11 +91,11 @@ public:
 private:
     /** Common signature for all the specialised add functions
      *
-     * @param[in]  input1 First input tensor. Data types supported: U8/QASYMM8/S16/QSYMM16/F16/S32/F32
-     * @param[in]  input2 Second input tensor. Data types supported: U8/QASYMM8/S16/QSYMM16/F16/S32/F32
-     * @param[out] output The output tensor. Data types supported: U8/QASYMM8/S16/QSYMM16/F16/S32/F32.
-     * @param[in]  policy Overflow policy.
-     * @param[in]  window Region on which to execute the kernel.
+     * @param[in, out] input1 First input tensor. Data types supported: U8/QASYMM8/S16/QSYMM16/F16/S32/F32
+     * @param[in]      input2 Second input tensor. Data types supported: U8/QASYMM8/S16/QSYMM16/F16/S32/F32
+     * @param[out]     output (Optional) The output tensor. Can be nullptr. Data types supported: U8/QASYMM8/S16/QSYMM16/F16/S32/F32.
+     * @param[in]      policy Overflow policy.
+     * @param[in]      window Region on which to execute the kernel.
      */
     using AddFunction = void(const ITensor *input1, const ITensor *input2, ITensor *output, ConvertPolicy policy, const Window &window);
     /** Add function to use for the particular tensor types passed to configure() */
diff --git a/arm_compute/runtime/NEON/functions/NEArithmeticAddition.h b/arm_compute/runtime/NEON/functions/NEArithmeticAddition.h
index bf8f2cc14b..5b430ce397 100644
--- a/arm_compute/runtime/NEON/functions/NEArithmeticAddition.h
+++ b/arm_compute/runtime/NEON/functions/NEArithmeticAddition.h
@@ -25,14 +25,14 @@
 #define ARM_COMPUTE_NEARITHMETICADDITION_H
 
 #include "arm_compute/core/Types.h"
-#include "arm_compute/runtime/NEON/INESimpleFunction.h"
+#include "arm_compute/runtime/NEON/INESimpleFunctionNoBorder.h"
 
 namespace arm_compute
 {
 class ITensor;
 
 /** Basic function to run @ref NEArithmeticAdditionKernel */
-class NEArithmeticAddition : public INESimpleFunction
+class NEArithmeticAddition : public INESimpleFunctionNoBorder
 {
 public:
     /** Initialise the kernel's inputs, output and conversion policy.
@@ -51,18 +51,18 @@ public:
      *   - (QASYMM8_SIGNED,QASYMM8_SIGNED) -> QASYMM8_SIGNED
      *   - (QSYMM16,QSYMM16) -> QSYMM16
      *
-     * @param[in]  input1   First tensor input. Data types supported: U8/QASYMM8/QASYMM8_SIGNED/S16/QSYMM16/F16/S32/F32
-     * @param[in]  input2   Second tensor input. Data types supported: U8/QASYMM8/QASYMM8_SIGNED/S16/QSYMM16/F16/S32/F32
-     * @param[out] output   Output tensor. Data types supported: U8/QASYMM8/QASYMM8_SIGNED/S16/QSYMM16/F16/S32/F32
-     * @param[in]  policy   Policy to use to handle overflow.
-     * @param[in]  act_info (Optional) Activation layer information in case of a fused activation. Currently not supported.
+     * @param[in, out] input1   First tensor input. Data types supported: U8/QASYMM8/QASYMM8_SIGNED/S16/QSYMM16/F16/S32/F32
+     * @param[in]      input2   Second tensor input. Data types supported: U8/QASYMM8/QASYMM8_SIGNED/S16/QSYMM16/F16/S32/F32
+     * @param[out]     output   (Optional) Output tensor. Can be nullptr. Data types supported: U8/QASYMM8/QASYMM8_SIGNED/S16/QSYMM16/F16/S32/F32
+     * @param[in]      policy   Policy to use to handle overflow.
+     * @param[in]      act_info (Optional) Activation layer information in case of a fused activation. Currently not supported.
      */
     void configure(ITensor *input1, ITensor *input2, ITensor *output, ConvertPolicy policy, const ActivationLayerInfo &act_info = ActivationLayerInfo());
     /** Static function to check if given info will lead to a valid configuration of @ref NEArithmeticAddition
      *
      * @param[in] input1   First tensor input info. Data types supported: U8/QASYMM8/QASYMM8_SIGNED/S16/QSYMM16/F16/S32/F32
      * @param[in] input2   Second tensor input info. Data types supported: U8/QASYMM8/QASYMM8_SIGNED/S16/QSYMM16/F16/S32/F32
-     * @param[in] output   Output tensor info. Data types supported: U8/SQASYMM8/QASYMM8_SIGNED/S16/QSYMM16/F16/S32/F32
+     * @param[in] output   (Optional) Output tensor info. Can be nullptr. Data types supported: U8/SQASYMM8/QASYMM8_SIGNED/S16/QSYMM16/F16/S32/F32
      * @param[in] policy   Policy to use to handle overflow
      * @param[in] act_info (Optional) Activation layer information in case of a fused activation. Currently not supported.
      *