24.02.1
|
#include <ClMatMulNativeKernel.h>
Public Member Functions | |
ClMatMulNativeKernel () | |
ARM_COMPUTE_DISALLOW_COPY_ALLOW_MOVE (ClMatMulNativeKernel) | |
void | configure (const ClCompileContext &compile_context, ITensorInfo *lhs, ITensorInfo *rhs, ITensorInfo *bias, ITensorInfo *dst, const MatMulKernelInfo &matmul_kernel_info, const ActivationLayerInfo &act_info=ActivationLayerInfo()) |
Initialise the kernel's input and output. More... | |
void | run_op (ITensorPack &tensors, const Window &window, cl::CommandQueue &queue) override |
Enqueue the OpenCL kernel to process the given window on the passed OpenCL command queue. More... | |
Public Member Functions inherited from ICLKernel | |
ICLKernel () | |
Constructor. More... | |
cl::Kernel & | kernel () |
Returns a reference to the OpenCL kernel of this object. More... | |
CLKernelType | type () const |
Returns the CL kernel type. More... | |
template<typename T > | |
void | add_1D_array_argument (unsigned int &idx, const ICLArray< T > *array, const Strides &strides, unsigned int num_dimensions, const Window &window) |
Add the passed 1D array's parameters to the object's kernel's arguments starting from the index idx. More... | |
void | add_1D_tensor_argument (unsigned int &idx, const ICLTensor *tensor, const Window &window) |
Add the passed 1D tensor's parameters to the object's kernel's arguments starting from the index idx. More... | |
void | add_1D_tensor_argument_if (bool cond, unsigned int &idx, const ICLTensor *tensor, const Window &window) |
Add the passed 1D tensor's parameters to the object's kernel's arguments starting from the index idx if the condition is true. More... | |
void | add_2D_tensor_argument (unsigned int &idx, const ICLTensor *tensor, const Window &window) |
Add the passed 2D tensor's parameters to the object's kernel's arguments starting from the index idx. More... | |
void | add_2D_tensor_argument_if (bool cond, unsigned int &idx, const ICLTensor *tensor, const Window &window) |
Add the passed 2D tensor's parameters to the object's kernel's arguments starting from the index idx if the condition is true. More... | |
void | add_3D_tensor_argument (unsigned int &idx, const ICLTensor *tensor, const Window &window) |
Add the passed 3D tensor's parameters to the object's kernel's arguments starting from the index idx. More... | |
void | add_4D_tensor_argument (unsigned int &idx, const ICLTensor *tensor, const Window &window) |
Add the passed 4D tensor's parameters to the object's kernel's arguments starting from the index idx. More... | |
void | add_5D_tensor_argument (unsigned int &idx, const ICLTensor *tensor, const Window &window) |
Add the passed 5D tensor's parameters to the object's kernel's arguments starting from the index idx. More... | |
void | add_3d_tensor_nhw_argument (unsigned int &idx, const ICLTensor *tensor) |
Add the passed NHW 3D tensor's parameters to the object's kernel's arguments by passing strides, dimensions and the offset to the first valid element in bytes. More... | |
void | add_4d_tensor_nhwc_argument (unsigned int &idx, const ICLTensor *tensor) |
Add the passed NHWC 4D tensor's parameters to the object's kernel's arguments by passing strides, dimensions and the offset to the first valid element in bytes. More... | |
virtual void | run (const Window &window, cl::CommandQueue &queue) |
Enqueue the OpenCL kernel to process the given window on the passed OpenCL command queue. More... | |
template<typename T > | |
void | add_argument (unsigned int &idx, T value) |
Add the passed parameters to the object's kernel's arguments starting from the index idx. More... | |
void | set_lws_hint (const cl::NDRange &lws_hint) |
Set the Local-Workgroup-Size hint. More... | |
cl::NDRange | lws_hint () const |
Return the Local-Workgroup-Size hint. More... | |
void | set_wbsm_hint (const cl_int &wbsm_hint) |
Set the workgroup batch size modifier hint. More... | |
cl_int | wbsm_hint () const |
Return the workgroup batch size modifier hint. More... | |
const std::string & | config_id () const |
Get the configuration ID. More... | |
void | set_target (GPUTarget target) |
Set the targeted GPU architecture. More... | |
void | set_target (cl::Device &device) |
Set the targeted GPU architecture according to the CL device. More... | |
GPUTarget | get_target () const |
Get the targeted GPU architecture. More... | |
size_t | get_max_workgroup_size () |
Get the maximum workgroup size for the device the CLKernelLibrary uses. More... | |
cl::NDRange | get_cached_gws () const |
Get the cached gws used to enqueue this kernel. More... | |
void | cache_gws (const cl::NDRange &gws) |
Cache the latest gws used to enqueue this kernel. More... | |
template<unsigned int dimension_size> | |
void | add_tensor_argument (unsigned &idx, const ICLTensor *tensor, const Window &window) |
template<typename T , unsigned int dimension_size> | |
void | add_array_argument (unsigned &idx, const ICLArray< T > *array, const Strides &strides, unsigned int num_dimensions, const Window &window) |
Add the passed array's parameters to the object's kernel's arguments starting from the index idx. More... | |
Public Member Functions inherited from IKernel | |
IKernel () | |
Constructor. More... | |
virtual | ~IKernel ()=default |
Destructor. More... | |
virtual bool | is_parallelisable () const |
Indicates whether or not the kernel is parallelisable. More... | |
virtual BorderSize | border_size () const |
The size of the border for that kernel. More... | |
const Window & | window () const |
The maximum window the kernel can be executed on. More... | |
bool | is_window_configured () const |
Function to check if the embedded window of this kernel has been configured. More... | |
Static Public Member Functions | |
static Status | validate (const ITensorInfo *lhs, const ITensorInfo *rhs, const ITensorInfo *bias, const ITensorInfo *dst, const MatMulKernelInfo &matmul_kernel_info, const ActivationLayerInfo &act_info=ActivationLayerInfo()) |
Static function to check if given info will lead to a valid configuration. More... | |
Static Public Member Functions inherited from ICLKernel | |
constexpr static unsigned int | num_arguments_per_3d_tensor_nhw () |
Returns the number of arguments enqueued per NHW 3D Tensor object. More... | |
constexpr static unsigned int | num_arguments_per_4d_tensor_nhwc () |
Returns the number of arguments enqueued per NHWC 4D Tensor object. More... | |
constexpr static unsigned int | num_arguments_per_1D_array () |
Returns the number of arguments enqueued per 1D array object. More... | |
constexpr static unsigned int | num_arguments_per_1D_tensor () |
Returns the number of arguments enqueued per 1D tensor object. More... | |
constexpr static unsigned int | num_arguments_per_2D_tensor () |
Returns the number of arguments enqueued per 2D tensor object. More... | |
constexpr static unsigned int | num_arguments_per_3D_tensor () |
Returns the number of arguments enqueued per 3D tensor object. More... | |
constexpr static unsigned int | num_arguments_per_4D_tensor () |
Returns the number of arguments enqueued per 4D tensor object. More... | |
static cl::NDRange | gws_from_window (const Window &window, bool use_dummy_work_items) |
Get the global work size given an execution window. More... | |
Definition at line 39 of file ClMatMulNativeKernel.h.
Definition at line 109 of file ClMatMulNativeKernel.cpp.
References arm_compute::GEMM.
ARM_COMPUTE_DISALLOW_COPY_ALLOW_MOVE | ( | ClMatMulNativeKernel | ) |
void configure | ( | const ClCompileContext & | compile_context, |
ITensorInfo * | lhs, | ||
ITensorInfo * | rhs, | ||
ITensorInfo * | bias, | ||
ITensorInfo * | dst, | ||
const MatMulKernelInfo & | matmul_kernel_info, | ||
const ActivationLayerInfo & | act_info = ActivationLayerInfo() |
||
) |
Initialise the kernel's input and output.
[in] | compile_context | The compile context to be used. |
[in] | lhs | Input tensor info for the LHS matrix. Data type supported: F32/F16. Dimensions above 2 are collapsed onto dimension 2 and represent the batch. |
[in] | rhs | Input tensor info for the RHS matrix. Data type supported: same as lhs . Dimensions above 2 are collapsed onto dimension 2 and represent the batch. |
[in] | bias | Bias tensor info for bias matrix. Can be nullptr. Data type supported: same as lhs . |
[out] | dst | Output tensor info. Data type supported: same as lhs |
[in] | matmul_kernel_info | Attributes for Batch MatMul Kernel |
[in] | act_info | (Optional) Specifies activation function to use after Matrix multiplication. Default is Identity function. |
Definition at line 150 of file ClMatMulNativeKernel.cpp.
References arm_compute::test::validation::act_info, CLBuildOptions::add_option(), CLBuildOptions::add_option_if(), CLBuildOptions::add_option_if_else(), MatMulKernelInfo::adj_lhs, MatMulKernelInfo::adj_rhs, arm_compute::adjust_vec_size(), ARM_COMPUTE_ERROR_ON_NULLPTR, ARM_COMPUTE_ERROR_THROW_ON, ARM_COMPUTE_LOG_PARAMS, arm_compute::auto_init_if_empty(), bias, arm_compute::calculate_max_window(), ICloneable< T >::clone(), Window::collapse(), arm_compute::misc::shape_calculator::compute_matmul_shape(), arm_compute::create_kernel(), ITensorInfo::data_type(), Window::DimZ, arm_compute::test::validation::dst, MatMulKernelInfo::export_rhs_to_cl_image, arm_compute::float_to_string_with_full_precision(), arm_compute::get_cl_type_from_data_type(), MatMulKernelInfo::k0, kernel_name, ITensorInfo::lock_paddings(), arm_compute::lower_string(), MatMulKernelInfo::m0, MatMulKernelInfo::n0, CLBuildOptions::options(), arm_compute::string_from_activation_func(), arm_compute::string_from_data_type(), ITensorInfo::tensor_shape(), arm_compute::support::cpp11::to_string(), arm_compute::opencl::kernels::gemm::update_padding_for_cl_image(), arm_compute::upper_string(), ClMatMulNativeKernel::validate(), Dimensions< T >::x(), and Dimensions< T >::y().
|
overridevirtual |
Enqueue the OpenCL kernel to process the given window on the passed OpenCL command queue.
[in] | tensors | A vector containing the tensors to operato on. |
[in] | window | Region on which to execute the kernel. (Must be a valid region of the window returned by window()). |
[in,out] | queue | Command queue on which to enqueue the kernel. |
Reimplemented from ICLKernel.
Definition at line 238 of file ClMatMulNativeKernel.cpp.
References arm_compute::ACL_DST, arm_compute::ACL_SRC_0, arm_compute::ACL_SRC_1, arm_compute::ACL_SRC_2, ICLKernel::add_3d_tensor_nhw_argument(), ARM_COMPUTE_ERROR_ON_INVALID_SUBWINDOW, ARM_COMPUTE_ERROR_ON_NULLPTR, ARM_COMPUTE_ERROR_ON_UNCONFIGURED_KERNEL, ARM_COMPUTE_LOG_PARAMS, bias, ICLTensor::cl_buffer(), Window::collapse(), arm_compute::test::validation::context, arm_compute::create_image2d_from_buffer(), ITensorInfo::data_type(), ITensorInfo::dimension(), Window::DimZ, arm_compute::test::validation::dst, arm_compute::enqueue(), CLKernelLibrary::get(), ITensorPack::get_const_tensor(), ITensorPack::get_tensor(), ITensor::info(), ICLKernel::lws_hint(), arm_compute::ReadOnly, ITensorInfo::strides_in_bytes(), ITensorInfo::tensor_shape(), TensorShape::total_size(), and IKernel::window().
|
static |
Static function to check if given info will lead to a valid configuration.
Similar to ClMatMulNativeKernel::configure()
Definition at line 114 of file ClMatMulNativeKernel.cpp.
References arm_compute::test::validation::act_info, ARM_COMPUTE_RETURN_ERROR_ON_DATA_TYPE_CHANNEL_NOT_IN, ARM_COMPUTE_RETURN_ERROR_ON_MISMATCHING_DATA_TYPES, ARM_COMPUTE_RETURN_ERROR_ON_MISMATCHING_SHAPES, ARM_COMPUTE_RETURN_ERROR_ON_MSG, ARM_COMPUTE_RETURN_ERROR_ON_NULLPTR, ARM_COMPUTE_RETURN_ON_ERROR, ARM_COMPUTE_UNUSED, bias, arm_compute::misc::shape_calculator::compute_matmul_shape(), arm_compute::test::validation::dst, arm_compute::F16, arm_compute::F32, ITensorInfo::tensor_shape(), and arm_compute::opencl::kernels::validate_matmul_input_shapes().
Referenced by ClMatMulNativeKernel::configure(), arm_compute::cl_matmul::select_info(), arm_compute::test::validation::TEST_CASE(), and ClMatMul::validate().