24.02.1
|
The CL kernel that performs softmax function. More...
#include <ClSoftmaxKernel.h>
Public Member Functions | |
ClSoftmaxKernel () | |
ARM_COMPUTE_DISALLOW_COPY_ALLOW_MOVE (ClSoftmaxKernel) | |
void | configure (const CLCompileContext &compile_context, const ITensorInfo &src, ITensorInfo &dst, const SoftmaxKernelInfo &info) |
Configure the kernel. 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... | |
const TensorInfo & | tmp_tensor_info () const |
Get the tensor info of the temporary tensor. 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 &src, const ITensorInfo &dst, const SoftmaxKernelInfo &info) |
Check if the kernel arguments are valid. 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... | |
The CL kernel that performs softmax function.
Definition at line 44 of file ClSoftmaxKernel.h.
ClSoftmaxKernel | ( | ) |
Definition at line 59 of file ClSoftmaxKernel.cpp.
ARM_COMPUTE_DISALLOW_COPY_ALLOW_MOVE | ( | ClSoftmaxKernel | ) |
void configure | ( | const CLCompileContext & | compile_context, |
const ITensorInfo & | src, | ||
ITensorInfo & | dst, | ||
const SoftmaxKernelInfo & | info | ||
) |
Configure the kernel.
[in] | compile_context | The compile context to be used. |
[in] | src | Source tensor info. Data types supported: QASYMM8/QASYMM8_SIGNED/F16/F32 for Softmax and F16/F32 for Log Softmax |
[out] | dst | Destination tensor info. Data types supported: same as src |
[in] | info | Contains information consumed by kernels for softmax described in SoftmaxKernelInfo. |
Definition at line 90 of file ClSoftmaxKernel.cpp.
References CLBuildOptions::add_option(), CLBuildOptions::add_option_if(), arm_compute::adjust_vec_size(), ARM_COMPUTE_ERROR_ON, ARM_COMPUTE_UNUSED, arm_compute::calculate_max_window(), Window::collapse_if_possible(), arm_compute::create_kernel(), arm_compute::test::validation::data_type, arm_compute::test::validation::dst, arm_compute::test::validation::dst_shape, arm_compute::F32, arm_compute::float_to_string_with_full_precision(), arm_compute::get_cl_type_from_data_type(), arm_compute::test::validation::info, kernel_name, arm_compute::lower_string(), Dimensions< T >::num_dimensions(), CLBuildOptions::options(), arm_compute::QASYMM8, arm_compute::QASYMM8_SIGNED, TensorShape::set(), Window::shift_dimensions(), arm_compute::test::validation::src, arm_compute::string_from_data_type(), arm_compute::to_string(), arm_compute::support::cpp11::to_string(), and arm_compute::wrap_around().
|
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 184 of file ClSoftmaxKernel.cpp.
References arm_compute::ACL_DST, arm_compute::ACL_INT_0, arm_compute::ACL_SRC, ARM_COMPUTE_ERROR_ON_INVALID_SUBWINDOW, ARM_COMPUTE_ERROR_ON_UNCONFIGURED_KERNEL, ICLTensor::cl_buffer(), arm_compute::test::validation::dst, arm_compute::enqueue(), ITensorPack::get_const_tensor(), ITensorPack::get_tensor(), ITensor::info(), ICLKernel::lws_hint(), TensorInfo::offset_first_element_in_bytes(), Dimensions< T >::remove(), arm_compute::test::validation::src, arm_compute::test::validation::src_info, ITensorInfo::strides_in_bytes(), TensorInfo::strides_in_bytes(), TensorInfo::total_size(), and IKernel::window().
const TensorInfo & tmp_tensor_info | ( | ) | const |
Get the tensor info of the temporary tensor.
Definition at line 256 of file ClSoftmaxKernel.cpp.
|
static |
Check if the kernel arguments are valid.
See ClSoftmaxKernel::configure().
Definition at line 63 of file ClSoftmaxKernel.cpp.
References ARM_COMPUTE_RETURN_ERROR_ON, ARM_COMPUTE_RETURN_ERROR_ON_DATA_TYPE_NOT_IN, ARM_COMPUTE_RETURN_ERROR_ON_MISMATCHING_DATA_TYPES, ARM_COMPUTE_RETURN_ERROR_ON_MISMATCHING_SHAPES, ARM_COMPUTE_UNUSED, arm_compute::test::validation::dst, arm_compute::F16, arm_compute::F32, arm_compute::get_softmax_output_quantization_info(), arm_compute::test::validation::info, arm_compute::is_data_type_quantized_asymmetric(), arm_compute::QASYMM8, arm_compute::QASYMM8_SIGNED, and arm_compute::test::validation::src.
Referenced by ClSoftmax::validate().