Compute Library
 21.02
CLLogits1DNormKernel Class Reference

Interface for calculating the final step of the Softmax Layer where each logit value is multiplied by the inverse of the sum of the logits. More...

#include <CLSoftmaxLayerKernel.h>

Collaboration diagram for CLLogits1DNormKernel:
[legend]

Public Member Functions

 CLLogits1DNormKernel ()
 Default constructor. More...
 
 CLLogits1DNormKernel (const CLLogits1DNormKernel &)=delete
 Prevent instances of this class from being copied (As this class contains pointers) More...
 
CLLogits1DNormKerneloperator= (const CLLogits1DNormKernel &)=delete
 Prevent instances of this class from being copied (As this class contains pointers) More...
 
 CLLogits1DNormKernel (CLLogits1DNormKernel &&)=default
 Allow instances of this class to be moved. More...
 
CLLogits1DNormKerneloperator= (CLLogits1DNormKernel &&)=default
 Allow instances of this class to be moved. More...
 
void configure (const ICLTensor *input, const ICLTensor *sum, ICLTensor *output, const SoftmaxKernelInfo &info)
 Set the input and output tensors. More...
 
void configure (const CLCompileContext &compile_context, const ICLTensor *input, const ICLTensor *sum, ICLTensor *output, const SoftmaxKernelInfo &info)
 Set the input and output tensors. More...
 
void run (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...
 
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...
 
virtual void run_op (ITensorPack &tensors, 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...
 
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 Windowwindow () const
 The maximum window the kernel can be executed on. More...
 

Static Public Member Functions

static Status validate (const ITensorInfo *input, const ITensorInfo *sum, const ITensorInfo *output, const SoftmaxKernelInfo &info)
 Static function to check if given info will lead to a valid configuration of CLLogits1DNormKernel. More...
 
- Static Public Member Functions inherited from ICLKernel
static constexpr unsigned int num_arguments_per_1D_array ()
 Returns the number of arguments enqueued per 1D array object. More...
 
static constexpr unsigned int num_arguments_per_1D_tensor ()
 Returns the number of arguments enqueued per 1D tensor object. More...
 
static constexpr unsigned int num_arguments_per_2D_tensor ()
 Returns the number of arguments enqueued per 2D tensor object. More...
 
static constexpr unsigned int num_arguments_per_3D_tensor ()
 Returns the number of arguments enqueued per 3D tensor object. More...
 
static constexpr 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)
 Get the global work size given an execution window. More...
 

Detailed Description

Interface for calculating the final step of the Softmax Layer where each logit value is multiplied by the inverse of the sum of the logits.

Definition at line 108 of file CLSoftmaxLayerKernel.h.

Constructor & Destructor Documentation

◆ CLLogits1DNormKernel() [1/3]

Default constructor.

Definition at line 282 of file CLSoftmaxLayerKernel.cpp.

283  : _input(nullptr), _sum(nullptr), _output(nullptr)
284 {
285 }

◆ CLLogits1DNormKernel() [2/3]

Prevent instances of this class from being copied (As this class contains pointers)

◆ CLLogits1DNormKernel() [3/3]

Allow instances of this class to be moved.

Member Function Documentation

◆ configure() [1/2]

void configure ( const ICLTensor input,
const ICLTensor sum,
ICLTensor output,
const SoftmaxKernelInfo info 
)

Set the input and output tensors.

Parameters
[in]inputSource tensor. Data types supported: S32/F16/F32. If this kernel is used for log softmax, only F32/F16 is supported.
[in]sumSum tensor. Dimensions should be dim(input)-1. Data types supported: same as input
[out]outputDestination tensor. Data types supported: QASYMM8/QASYMM8_SIGNED for S32 input, or same as input
[in]infoContains information consumed by kernels for softmax described in SoftmaxKernelInfo.

Definition at line 287 of file CLSoftmaxLayerKernel.cpp.

References CLKernelLibrary::get().

288 {
289  configure(CLKernelLibrary::get().get_compile_context(), input, sum, output, info);
290 }
DATA_TYPE sum(__global const DATA_TYPE *input)
Calculate sum of a vector.
static CLKernelLibrary & get()
Access the KernelLibrary singleton.
void configure(const ICLTensor *input, const ICLTensor *sum, ICLTensor *output, const SoftmaxKernelInfo &info)
Set the input and output tensors.
ScaleKernelInfo info(interpolation_policy, default_border_mode, PixelValue(), sampling_policy, false)

◆ configure() [2/2]

void configure ( const CLCompileContext compile_context,
const ICLTensor input,
const ICLTensor sum,
ICLTensor output,
const SoftmaxKernelInfo info 
)

Set the input and output tensors.

Parameters
[in]compile_contextThe compile context to be used.
[in]inputSource tensor. Data types supported: S32/F16/F32. If this kernel is used for log softmax, only F32/F16 is supported.
[in]sumSum tensor. Dimensions should be dim(input)-1. Data types supported: same as input
[out]outputDestination tensor. Data types supported: QASYMM8/QASYMM8_SIGNED for S32 input, or same as input
[in]infoContains information consumed by kernels for softmax described in SoftmaxKernelInfo.

Definition at line 292 of file CLSoftmaxLayerKernel.cpp.

References CLBuildOptions::add_option(), arm_compute::adjust_vec_size(), ARM_COMPUTE_ERROR_ON, ARM_COMPUTE_ERROR_ON_NULLPTR, ARM_COMPUTE_ERROR_THROW_ON, arm_compute::auto_init_if_empty(), SoftmaxKernelInfo::beta, arm_compute::calculate_max_window(), ICloneable< T >::clone(), arm_compute::create_kernel(), ITensorInfo::dimension(), arm_compute::get_cl_type_from_data_type(), arm_compute::get_padding_info(), arm_compute::get_softmax_output_quantization_info(), arm_compute::has_padding_changed(), ITensor::info(), arm_compute::test::validation::info, arm_compute::test::validation::input, SoftmaxKernelInfo::input_data_type, arm_compute::is_data_type_quantized_asymmetric(), arm_compute::is_data_type_quantized_asymmetric_signed(), SoftmaxKernelInfo::is_log, kernel_name, arm_compute::test::validation::qinfo, ITensorInfo::quantization_info(), UniformQuantizationInfo::scale, sum(), arm_compute::support::cpp11::to_string(), and QuantizationInfo::uniform().

293 {
295 
296  auto padding_info = get_padding_info({ input, output, sum });
297 
298  // Note: output should always have a scale of 1/256 and offset 0
299  const bool is_quantized_asymmetric = is_data_type_quantized_asymmetric(info.input_data_type);
300  const DataType output_data_type = info.input_data_type;
301  const QuantizationInfo allowed_quantization_info = get_softmax_output_quantization_info(info.input_data_type, info.is_log);
302  const UniformQuantizationInfo qinfo = input->info()->quantization_info().uniform();
303 
304  // Output auto initialization if not yet initialized
305  auto_init_if_empty(*output->info(),
306  input->info()->clone()->set_data_type(output_data_type).set_quantization_info(allowed_quantization_info));
307 
308  // Perform validation step
309  ARM_COMPUTE_ERROR_THROW_ON(validate_arguments_1DNorm(input->info(), sum->info(), output->info(), info));
310 
311  _input = input;
312  _sum = sum;
313  _output = output;
314 
315  const auto is_signed_qasymm8 = is_data_type_quantized_asymmetric_signed(info.input_data_type);
316  const int min_value = is_signed_qasymm8 ? CL_SCHAR_MIN : 0;
317  const unsigned int vector_size = adjust_vec_size(16, input->info()->dimension(0));
318 
319  // Set build options
320  CLBuildOptions build_opts;
321  build_opts.add_option("-DDATA_TYPE=" + get_cl_type_from_data_type(info.input_data_type));
322  build_opts.add_option("-DMIN_VALUE=" + support::cpp11::to_string(min_value));
323  build_opts.add_option("-DVECTOR_SIZE=" + support::cpp11::to_string(vector_size));
324  build_opts.add_option("-DVECTOR_SIZE_LEFTOVER=" + support::cpp11::to_string(input->info()->dimension(0) % vector_size));
325  build_opts.add_option_if(is_data_type_quantized_asymmetric_signed(info.input_data_type), "-DQASYMM8_SIGNED");
326  build_opts.add_options_if(is_quantized_asymmetric,
327  prepare_quantized_softmax_build_options(qinfo.scale, info.beta).options());
328  build_opts.add_option_if(info.is_log, "-DLOG_SOFTMAX");
329 
330  // Create kernel
331  std::string kernel_name = std::string("softmax_layer_norm") + (is_quantized_asymmetric ? "_quantized" : "");
332  _kernel = create_kernel(compile_context, kernel_name, build_opts.options());
333 
334  // Configure window
335  auto win = calculate_max_window(*(input->info()), Steps(vector_size));
336  ICLKernel::configure_internal(win);
337 
339 }
Window calculate_max_window(const ValidRegion &valid_region, const Steps &steps, bool skip_border, BorderSize border_size)
DATA_TYPE sum(__global const DATA_TYPE *input)
Calculate sum of a vector.
std::string to_string(T &&value)
Convert integer and float values to string.
#define ARM_COMPUTE_ERROR_ON(cond)
If the condition is true then an error message is printed and an exception thrown.
Definition: Error.h:466
QuantizationInfo get_softmax_output_quantization_info(DataType input_type, bool is_log)
Returns output quantization information for softmax layer.
Definition: Utils.cpp:462
#define ARM_COMPUTE_ERROR_THROW_ON(status)
Definition: Error.h:455
cl::Kernel create_kernel(const CLCompileContext &ctx, const std::string &kernel_name, const std::set< std::string > &build_opts=std::set< std::string >())
Creates an opencl kernel using a compile context.
Definition: CLHelpers.cpp:403
std::string kernel_name
std::string get_cl_type_from_data_type(const DataType &dt)
Translates a tensor data type to the appropriate OpenCL type.
Definition: CLHelpers.cpp:37
bool is_data_type_quantized_asymmetric_signed(DataType dt)
Check if a given data type is of asymmetric quantized signed type.
Definition: Utils.h:1209
bool auto_init_if_empty(ITensorInfo &info, const TensorShape &shape, int num_channels, DataType data_type, QuantizationInfo quantization_info=QuantizationInfo())
Auto initialize the tensor info (shape, number of channels and data type) if the current assignment i...
bool has_padding_changed(const std::unordered_map< const ITensorInfo *, PaddingSize > &padding_map)
Check if the previously stored padding info has changed after configuring a kernel.
Definition: Utils.cpp:528
bool is_data_type_quantized_asymmetric(DataType dt)
Check if a given data type is of asymmetric quantized type.
Definition: Utils.h:1190
ScaleKernelInfo info(interpolation_policy, default_border_mode, PixelValue(), sampling_policy, false)
const QuantizationInfo qinfo
Definition: Im2Col.cpp:155
std::unordered_map< const ITensorInfo *, PaddingSize > get_padding_info(std::initializer_list< const ITensorInfo *> infos)
Stores padding information before configuring a kernel.
Definition: Utils.cpp:513
#define ARM_COMPUTE_ERROR_ON_NULLPTR(...)
Definition: Validate.h:161
unsigned int adjust_vec_size(unsigned int vec_size, size_t dim0)
Returns the adjusted vector size in case it is less than the input&#39;s first dimension, getting rounded down to its closest valid vector size.
Definition: Utils.h:1358
DataType
Available data types.
Definition: Types.h:77

◆ operator=() [1/2]

CLLogits1DNormKernel& operator= ( const CLLogits1DNormKernel )
delete

Prevent instances of this class from being copied (As this class contains pointers)

◆ operator=() [2/2]

CLLogits1DNormKernel& operator= ( CLLogits1DNormKernel &&  )
default

Allow instances of this class to be moved.

◆ run()

void run ( const Window window,
cl::CommandQueue &  queue 
)
overridevirtual

Enqueue the OpenCL kernel to process the given window on the passed OpenCL command queue.

Note
The queue is not flushed by this method, and therefore the kernel will not have been executed by the time this method returns.
Parameters
[in]windowRegion on which to execute the kernel. (Must be a valid region of the window returned by window()).
[in,out]queueCommand queue on which to enqueue the kernel.

Reimplemented from ICLKernel.

Definition at line 348 of file CLSoftmaxLayerKernel.cpp.

References ICLKernel::add_3D_tensor_argument(), ARM_COMPUTE_ERROR_ON_INVALID_SUBWINDOW, ARM_COMPUTE_ERROR_ON_UNCONFIGURED_KERNEL, Window::collapse_if_possible(), Window::DimX, Window::DimZ, arm_compute::enqueue(), Window::first_slice_window_3D(), ICLKernel::lws_hint(), Window::set(), arm_compute::test::validation::reference::slice(), Window::slide_window_slice_3D(), and IKernel::window().

349 {
352 
353  Window window_collapsed = window.collapse_if_possible(ICLKernel::window(), Window::DimZ);
354  Window slice = window_collapsed.first_slice_window_3D();
355 
356  do
357  {
358  Window sum_slice = slice;
359  sum_slice.set(Window::DimX, Window::Dimension(0, 1, 1));
360 
361  unsigned int idx = 0;
362  // Set inputs
363  add_3D_tensor_argument(idx, _input, slice);
364  add_3D_tensor_argument(idx, _sum, sum_slice);
365  add_3D_tensor_argument(idx, _output, slice);
366  enqueue(queue, *this, slice, lws_hint());
367  }
368  while(window_collapsed.slide_window_slice_3D(slice));
369 }
const Window & window() const
The maximum window the kernel can be executed on.
Definition: IKernel.cpp:28
void enqueue(IGCKernel &kernel, const Window &window, const gles::NDRange &lws=gles::NDRange(1U, 1U, 1U))
Add the kernel to the command queue with the given window.
Definition: IGCKernel.cpp:41
cl::NDRange lws_hint() const
Return the Local-Workgroup-Size hint.
Definition: ICLKernel.h:276
void add_3D_tensor_argument(unsigned int &idx, const ICLTensor *tensor, const Window &window)
Add the passed 3D tensor&#39;s parameters to the object&#39;s kernel&#39;s arguments starting from the index idx...
Definition: ICLKernel.h:172
static constexpr size_t DimX
Alias for dimension 0 also known as X dimension.
Definition: Window.h:43
Window collapse_if_possible(const Window &full_window, size_t first, size_t last, bool *has_collapsed=nullptr) const
Collapse the dimensions between first and last if possible.
Definition: Window.inl:68
#define ARM_COMPUTE_ERROR_ON_UNCONFIGURED_KERNEL(k)
Definition: Validate.h:941
static constexpr size_t DimZ
Alias for dimension 2 also known as Z dimension.
Definition: Window.h:47
#define ARM_COMPUTE_ERROR_ON_INVALID_SUBWINDOW(f, s)
Definition: Validate.h:205
SimpleTensor< T > slice(const SimpleTensor< T > &src, Coordinates starts, Coordinates ends)

◆ validate()

Status validate ( const ITensorInfo input,
const ITensorInfo sum,
const ITensorInfo output,
const SoftmaxKernelInfo info 
)
static

Static function to check if given info will lead to a valid configuration of CLLogits1DNormKernel.

Parameters
[in]inputSource tensor. Data types supported: S32/F16/F32. If this kernel is used for log softmax, only F32/F16 is supported.
[in]sumSum tensor. Dimensions should be dim(input)-1. Data types supported: same as input
[in]outputDestination tensor. Data types supported: QASYMM8 for S32 input, or same as input
[in]infoContains information consumed by kernels for softmax described in SoftmaxKernelInfo.
Returns
a status

Definition at line 341 of file CLSoftmaxLayerKernel.cpp.

References ARM_COMPUTE_RETURN_ON_ERROR.

Referenced by CLSoftmaxLayerGeneric< IS_LOG >::validate().

342 {
343  ARM_COMPUTE_RETURN_ON_ERROR(validate_arguments_1DNorm(input, sum, output, info));
344 
345  return Status{};
346 }
DATA_TYPE sum(__global const DATA_TYPE *input)
Calculate sum of a vector.
#define ARM_COMPUTE_RETURN_ON_ERROR(status)
Checks if a status contains an error and returns it.
Definition: Error.h:204
ScaleKernelInfo info(interpolation_policy, default_border_mode, PixelValue(), sampling_policy, false)

The documentation for this class was generated from the following files: