COMPMID-2171: Fuse bias addition with CLGEMMMatrixMultiplyReshapedOnlyRHSKernel
Change-Id: I1d1e1f28fe7022309d72900893e8368820ca0f89
Signed-off-by: giuros01 <giuseppe.rossini@arm.com>
Reviewed-on: https://review.mlplatform.org/c/1259
Comments-Addressed: Arm Jenkins <bsgcomp@arm.com>
Reviewed-by: Michele Di Giorgio <michele.digiorgio@arm.com>
Reviewed-by: Gian Marco Iodice <gianmarco.iodice@arm.com>
Tested-by: Arm Jenkins <bsgcomp@arm.com>
diff --git a/arm_compute/core/CL/kernels/CLGEMMMatrixMultiplyReshapedOnlyRHSKernel.h b/arm_compute/core/CL/kernels/CLGEMMMatrixMultiplyReshapedOnlyRHSKernel.h
index 26a1378..e3b3880 100644
--- a/arm_compute/core/CL/kernels/CLGEMMMatrixMultiplyReshapedOnlyRHSKernel.h
+++ b/arm_compute/core/CL/kernels/CLGEMMMatrixMultiplyReshapedOnlyRHSKernel.h
@@ -51,8 +51,10 @@
*
* @param[in] input0 Input tensor containing the LHS 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 to retrieve the number of rows to be processed by each thread. Only the following values are supported:
* lhs_info.m0: 1,2,3,4,5,6,7,8
* @param[in] rhs_info RHS matrix information used for reshaping the input1 tensor. Only the following values are supported:
@@ -61,14 +63,17 @@
* rhs_info.transpose: true,false
* @param[in] gemm_info GEMM information used to retrieve the original dimensions of the input matrices
*/
- 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 CLGEMMMatrixMultiplyReshapedOnlyRHSKernel
*
* @param[in] input0 Input tensor info for the LHS 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 info for 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 info. 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 to retrieve the number of rows to be processed by each thread. Only the following values are supported:
* lhs_info.m0: 1,2,3,4,5,6,7,8
* @param[in] rhs_info RHS matrix information used for reshaping the input1 tensor. Only the following values are supported:
@@ -79,8 +84,9 @@
*
* @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;
@@ -88,11 +94,14 @@
private:
const ICLTensor *_input0;
const ICLTensor *_input1;
+ const ICLTensor *_input2;
ICLTensor *_output;
bool _slide_matrix_b;
bool _reinterpret_input_as_3d;
bool _reinterpret_output_as_3d;
bool _use_dummy_work_items;
+ bool _add_bias;
+ bool _broadcast_bias;
};
} // namespace arm_compute
-#endif /*__ARM_COMPUTE_CLGEMMMATRIXMULTIPLYRESHAPEDONLYRHSKERNEL_H__*/
\ No newline at end of file
+#endif /*__ARM_COMPUTE_CLGEMMMATRIXMULTIPLYRESHAPEDONLYRHSKERNEL_H__*/