diff options
Diffstat (limited to 'arm_compute')
-rw-r--r-- | arm_compute/core/CL/kernels/CLGEMMMatrixMultiplyReshapedOnlyRHSKernel.h | 43 |
1 files changed, 40 insertions, 3 deletions
diff --git a/arm_compute/core/CL/kernels/CLGEMMMatrixMultiplyReshapedOnlyRHSKernel.h b/arm_compute/core/CL/kernels/CLGEMMMatrixMultiplyReshapedOnlyRHSKernel.h index f7d314a039..8f60557c01 100644 --- a/arm_compute/core/CL/kernels/CLGEMMMatrixMultiplyReshapedOnlyRHSKernel.h +++ b/arm_compute/core/CL/kernels/CLGEMMMatrixMultiplyReshapedOnlyRHSKernel.h @@ -51,7 +51,19 @@ public: CLGEMMMatrixMultiplyReshapedOnlyRHSKernel &operator=(CLGEMMMatrixMultiplyReshapedOnlyRHSKernel &&) = default; /** Initialise the kernel's input and output. * - * @param[in] input0 Input tensor containing the LHS matrix. Data type supported: F16/F32. The number of dimensions for the LHS matrix must be less or equal than 4. + * @note If rhs_info.export_to_cl_image = true, this OpenCL kernel will fetch the RHS data using the OpenCL read_image built-in function. + * Reading from the OpenCL image object can increase the performance. However, since the OpenCL image object is created importing the OpenCL buffer, + * the following conditions are required: + * -# rhs_info.n0 can only be 4, 8 and 16 + * -# rhs_info.k0 can only be 4, 8 and 16 + * -# Data type can only be F32 + * -# The platform should support the OpenCL cl_khr_image2d_from_buffer extension + * -# The stride Y for the input1 should satisfy the OpenCL pitch alignment requirement + * -# input1 width should be less or equal to (CL_DEVICE_IMAGE2D_MAX_WIDTH * 4) + * -# input1 (height * depth) should be less or equal to CL_DEVICE_IMAGE2D_MAX_HEIGHT + * + * @param[in] input0 Input tensor containing the LHS matrix. Data type supported: F16/F32 (only F32 if rhs_info.export_to_cl_image = true). + * 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 @@ -70,8 +82,20 @@ public: const GEMMKernelInfo &gemm_info); /** Initialise the kernel's input and output. * + * @note If rhs_info.export_to_cl_image = true, this OpenCL kernel will fetch the RHS data using the OpenCL read_image built-in function. + * Reading from the OpenCL image object can increase the performance. However, since the OpenCL image object is created importing the OpenCL buffer, + * the following conditions are required: + * -# rhs_info.n0 can only be 4, 8 and 16 + * -# rhs_info.k0 can only be 4, 8 and 16 + * -# Data type can only be F32 + * -# The platform should support the OpenCL cl_khr_image2d_from_buffer extension + * -# The stride Y for the input1 should satisfy the OpenCL pitch alignment requirement + * -# input1 width should be less or equal to (CL_DEVICE_IMAGE2D_MAX_WIDTH * 4) + * -# input1 (height * depth) should be less or equal to CL_DEVICE_IMAGE2D_MAX_HEIGHT + * * @param[in] compile_context The compile context to be used. - * @param[in] input0 Input tensor containing the LHS matrix. Data type supported: F16/F32. The number of dimensions for the LHS matrix must be less or equal than 4. + * @param[in] input0 Input tensor containing the LHS matrix. Data type supported: F16/F32 (only F32 if rhs_info.export_to_cl_image = true). + * 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 @@ -91,7 +115,19 @@ public: const GEMMKernelInfo &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: F16/F32. The number of dimensions for the LHS matrix must be less or equal than 4. + * @note If rhs_info.export_to_cl_image = true, this OpenCL kernel will fetch the RHS data using the OpenCL read_image built-in function. + * Reading from the OpenCL image object can increase the performance. However, since the OpenCL image object is created importing the OpenCL buffer, + * the following conditions are required: + * -# rhs_info.n0 can only be 4, 8 and 16 + * -# rhs_info.k0 can only be 4, 8 and 16 + * -# Data type can only be F32 + * -# The platform should support the OpenCL cl_khr_image2d_from_buffer extension + * -# The stride Y for the input1 should satisfy the OpenCL pitch alignment requirement + * -# input1 width should be less or equal to (CL_DEVICE_IMAGE2D_MAX_WIDTH * 4) + * -# input1 (height * depth) should be less or equal to CL_DEVICE_IMAGE2D_MAX_HEIGHT + * + * @param[in] input0 Input tensor info for the LHS matrix. Data type supported: F16/F32 (only F32 if rhs_info.export_to_cl_image = true). + * 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 @@ -125,6 +161,7 @@ private: bool _use_dummy_work_items; bool _add_bias; bool _broadcast_bias; + bool _export_to_cl_image; }; } // namespace arm_compute #endif /*ARM_COMPUTE_CLGEMMMATRIXMULTIPLYRESHAPEDONLYRHSKERNEL_H*/ |