diff options
Diffstat (limited to 'arm_compute/core/CL/kernels/CLGEMMMatrixMultiplyReshapedKernel.h')
-rw-r--r-- | arm_compute/core/CL/kernels/CLGEMMMatrixMultiplyReshapedKernel.h | 31 |
1 files changed, 30 insertions, 1 deletions
diff --git a/arm_compute/core/CL/kernels/CLGEMMMatrixMultiplyReshapedKernel.h b/arm_compute/core/CL/kernels/CLGEMMMatrixMultiplyReshapedKernel.h index 449c333143..45df67673c 100644 --- a/arm_compute/core/CL/kernels/CLGEMMMatrixMultiplyReshapedKernel.h +++ b/arm_compute/core/CL/kernels/CLGEMMMatrixMultiplyReshapedKernel.h @@ -1,5 +1,5 @@ /* - * Copyright (c) 2018-2019 ARM Limited. + * Copyright (c) 2018-2020 ARM Limited. * * SPDX-License-Identifier: MIT * @@ -76,6 +76,35 @@ public: 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 GEMMKernelInfo &gemm_info); + /** Initialise the kernel's input and output. + * + * @note The F16 computation also supports mixed precision through the gemm_info.fp_mixed_precision flag. + * Mixed precision combines different floating precisions during the computation, in particular, F32 for the accumulations and F16 for the + * multiplications. i.e. float c = (half)a * (half)b + * + * @param[in] compile_context The compile context to be used. + * @param[in] input0 Input tensor containing the LHS reshaped matrix. Data type supported: F16/F32. 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 + * lhs_info.transpose: false + * @param[in] rhs_info RHS matrix information used for reshaping the input1 tensor. Only the following values are supported: + * rhs_info.n0: 2,3,4,8,16 + * rhs_info.k0: 2,3,4,8,16 + * rhs_info.transpose: true + * @param[in] gemm_info GEMM information used to retrieve the original dimensions of the input matrices + * + * @note lhs_info.k0 must be equal to rhs_info.k0 + */ + void configure(CLCompileContext &compile_context, const ICLTensor *input0, const ICLTensor *input1, const ICLTensor *input2, ICLTensor *output, float alpha, float beta, + const GEMMLHSMatrixInfo &lhs_info, + const GEMMRHSMatrixInfo &rhs_info, + const GEMMKernelInfo &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: F16/F32. The number of dimensions for the LHS matrix must be less or equal than 4 |