COMPMID-2053: Fuse bias addition with CLGEMMMatrixMultiplyReshapedKernel

Change-Id: I5bfd38c94a6fd18a1cba2104f7e1b04e7bef6ec2
Signed-off-by: Gian Marco Iodice <gianmarco.iodice@arm.com>
Reviewed-on: https://review.mlplatform.org/c/1359
Comments-Addressed: Arm Jenkins <bsgcomp@arm.com>
Reviewed-by: Georgios Pinitas <georgios.pinitas@arm.com>
Tested-by: Arm Jenkins <bsgcomp@arm.com>
diff --git a/arm_compute/core/CL/kernels/CLGEMMMatrixMultiplyReshapedKernel.h b/arm_compute/core/CL/kernels/CLGEMMMatrixMultiplyReshapedKernel.h
index 4052a09..68ab94a 100644
--- a/arm_compute/core/CL/kernels/CLGEMMMatrixMultiplyReshapedKernel.h
+++ b/arm_compute/core/CL/kernels/CLGEMMMatrixMultiplyReshapedKernel.h
@@ -51,8 +51,10 @@
      *
      * @param[in]  input0    Input tensor containing the LHS reshaped matrix. Data type supported: F32/F16. The number of dimensions for the LHS matrix must be less or equal than 4
      * @param[in]  input1    Input tensor containing the RHS reshaped matrix. Data type supported: same as @p input0. The number of dimensions for the RHS matrix must be less or equal than 3
+     * @param[in]  input2    Input tensor containing the bias matrix. Data type supported: same as @p input0.
      * @param[out] output    Output tensor to store the result of matrix multiplication. Data type supported: same as @p input0
      * @param[in]  alpha     Weight of the matrix product
+     * @param[in]  beta      Weight of the matrix bias
      * @param[in]  lhs_info  LHS matrix information used for reshaping the input0 tensor.  Only the following values are supported:
      *                       lhs_info.m0: 2,3,4,5,6,7,8
      *                       lhs_info.k0: 2,3,4,8,16
@@ -65,14 +67,17 @@
      *
      * @note lhs_info.k0 must be equal to rhs_info.k0
      */
-    void configure(const ICLTensor *input0, const ICLTensor *input1, ICLTensor *output, float alpha, const GEMMLHSMatrixInfo &lhs_info, const GEMMRHSMatrixInfo &rhs_info,
-                   const GEMMReshapeInfo &gemm_info);
+    void configure(const ICLTensor *input0, const ICLTensor *input1, const ICLTensor *input2, ICLTensor *output, float alpha, float beta, const GEMMLHSMatrixInfo &lhs_info,
+                   const GEMMRHSMatrixInfo &rhs_info,
+                   const GEMMReshapeInfo   &gemm_info);
     /** Static function to check if given info will lead to a valid configuration of @ref CLGEMMMatrixMultiplyReshapedKernel
      *
      * @param[in] input0    Input tensor containing the LHS reshaped matrix. Data type supported: F32/F16. The number of dimensions for the LHS matrix must be less or equal than 4
      * @param[in] input1    Input tensor containing the RHS reshaped matrix. Data type supported: same as @p input0. The number of dimensions for the RHS matrix must be less or equal than 3
+     * @param[in] input2    Input tensor info containing the bias matrix. Data type supported: same as @p input0.
      * @param[in] output    Output tensor to store the result of matrix multiplication. Data type supported: same as @p input0
      * @param[in] alpha     Weight of the matrix product
+     * @param[in] beta      Weight of the matrix bias
      * @param[in] lhs_info  LHS matrix information used for reshaping the input0 tensor.  Only the following values are supported:
      *                      lhs_info.m0: 2,3,4,5,6,7,8
      *                      lhs_info.k0: 2,3,4,8,16
@@ -87,8 +92,9 @@
      *
      * @return a status
      */
-    static Status validate(const ITensorInfo *input0, const ITensorInfo *input1, const ITensorInfo *output, float alpha, const GEMMLHSMatrixInfo &lhs_info, const GEMMRHSMatrixInfo &rhs_info,
-                           const GEMMReshapeInfo &gemm_info);
+    static Status validate(const ITensorInfo *input0, const ITensorInfo *input1, const ITensorInfo *input2, const ITensorInfo *output, float alpha, float beta, const GEMMLHSMatrixInfo &lhs_info,
+                           const GEMMRHSMatrixInfo &rhs_info,
+                           const GEMMReshapeInfo   &gemm_info);
 
     // Inherited methods overridden:
     void run(const Window &window, cl::CommandQueue &queue) override;
@@ -96,11 +102,14 @@
 private:
     const ICLTensor *_input0;
     const ICLTensor *_input1;
+    const ICLTensor *_input2;
     ICLTensor       *_output;
     bool             _slide_matrix_b;
     bool             _reinterpret_output_as_3d;
     unsigned int     _k;
     bool             _use_dummy_work_items;
+    bool             _add_bias;
+    bool             _broadcast_bias;
 };
 } // namespace arm_compute
 #endif /*__ARM_COMPUTE_CLGEMMMATRIXMULTIPLYRESHAPEDKERNEL_H__*/
\ No newline at end of file