Compute Library
 19.08
GCLogits1DNormKernel 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 <GCSoftmaxLayerKernel.h>

Collaboration diagram for GCLogits1DNormKernel:
[legend]

Public Member Functions

 GCLogits1DNormKernel ()
 Default constructor. More...
 
 GCLogits1DNormKernel (const GCLogits1DNormKernel &)=delete
 Prevent instances of this class from being copied (As this class contains pointers) More...
 
GCLogits1DNormKerneloperator= (const GCLogits1DNormKernel &)=delete
 Prevent instances of this class from being copied (As this class contains pointers) More...
 
 GCLogits1DNormKernel (GCLogits1DNormKernel &&)=default
 Allow instances of this class to be moved. More...
 
GCLogits1DNormKerneloperator= (GCLogits1DNormKernel &&)=default
 Allow instances of this class to be moved. More...
 
void configure (const IGCTensor *input, const IGCTensor *sum, IGCTensor *output)
 Set the input and output tensors. More...
 
void run (const Window &window) override
 Enqueue the OpenGL ES shader to process the given window. More...
 
- Public Member Functions inherited from IGCKernel
 IGCKernel ()
 Constructor. More...
 
GCKernelkernel ()
 Returns a reference to the GLES kernel of this object. More...
 
void add_1D_tensor_argument (unsigned int &idx, const IGCTensor *tensor, const unsigned int binding_point, 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_2D_tensor_argument (unsigned int &idx, const IGCTensor *tensor, const unsigned int binding_point, 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_3D_tensor_argument (unsigned int &idx, const IGCTensor *tensor, const unsigned int binding_point, const Window &window)
 Add the passed 3D tensor's parameters to the object's kernel's arguments starting from the index idx. More...
 
unsigned int num_arguments_per_1D_tensor () const
 Returns the number of arguments enqueued per 1D tensor object. More...
 
unsigned int num_arguments_per_2D_tensor () const
 Returns the number of arguments enqueued per 2D tensor object. More...
 
unsigned int num_arguments_per_3D_tensor () const
 Returns the number of arguments enqueued per 3D tensor object. More...
 
void set_lws_hint (gles::NDRange &lws_hint)
 Set the Local-Workgroup-Size hint. More...
 
void set_target (GPUTarget target)
 Set the targeted GPU architecture. More...
 
GPUTarget get_target () const
 Get the targeted GPU architecture. 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...
 

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 79 of file GCSoftmaxLayerKernel.h.

Constructor & Destructor Documentation

◆ GCLogits1DNormKernel() [1/3]

Default constructor.

Definition at line 196 of file GCSoftmaxLayerKernel.cpp.

197  : _input(nullptr), _sum(nullptr), _output(nullptr)
198 {
199 }

◆ GCLogits1DNormKernel() [2/3]

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

◆ GCLogits1DNormKernel() [3/3]

Allow instances of this class to be moved.

Member Function Documentation

◆ configure()

void configure ( const IGCTensor input,
const IGCTensor sum,
IGCTensor output 
)

Set the input and output tensors.

Parameters
[in]inputSource tensor. Data types supported: F16/F32
[in]sumSum tensor. Dimensions should be dim(input)-1. Data types supported: same as input
[out]outputDestination tensor. Data types supported: same as input

Definition at line 201 of file GCSoftmaxLayerKernel.cpp.

202 {
205 
206  // Output auto initialization if not yet initialized
207  auto_init_if_empty(*output->info(), input->info()->tensor_shape(), 1, input->info()->data_type());
208 
211 
212  _input = input;
213  _sum = sum;
214  _output = output;
215 
216  // Set build options
217  std::set<std::string> build_opts;
218  std::string dt_name = (input->info()->data_type() == DataType::F32) ? "DATA_TYPE_FP32" : "DATA_TYPE_FP16";
219  build_opts.insert("#define " + dt_name);
220  build_opts.emplace("#define LOCAL_SIZE_X " + support::cpp11::to_string(1));
221  build_opts.emplace("#define LOCAL_SIZE_Y " + support::cpp11::to_string(1));
222  build_opts.emplace("#define LOCAL_SIZE_Z " + support::cpp11::to_string(1));
223  build_opts.insert("#define SOFTMAX_LAYER_NORM");
224 
225  // Create kernel
226  _kernel = static_cast<GCKernel>(GCKernelLibrary::get().create_kernel("softmax_layer_norm", build_opts));
227 
228  // Configure window
229  constexpr unsigned int num_elems_processed_per_iteration = 8;
230  unsigned int num_elems_written_per_iteration = 1;
231  if(input->info()->data_type() == DataType::F16)
232  {
233  num_elems_written_per_iteration = 2;
234  }
235 
236  Window win = calculate_max_window(*input->info(), Steps(num_elems_processed_per_iteration));
237 
238  AccessWindowHorizontal input_access(input->info(), 0, num_elems_processed_per_iteration);
239  AccessWindowStatic sum_access(sum->info(), 0, 0, num_elems_written_per_iteration, sum->info()->dimension(1));
240  AccessWindowHorizontal output_access(output->info(), 0, num_elems_processed_per_iteration);
241 
242  update_window_and_padding(win, input_access, sum_access, output_access);
243 
244  output_access.set_valid_region(win, input->info()->valid_region());
245 
246  IGCKernel::configure(win);
247 }
#define ARM_COMPUTE_ERROR_ON_MISMATCHING_DATA_TYPES(...)
Definition: Validate.h:543
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.
virtual DataType data_type() const =0
Data type used for each element of the tensor.
1 channel, 1 F32 per channel
Window calculate_max_window(const ValidRegion &valid_region, const Steps &steps=Steps(), bool skip_border=false, BorderSize border_size=BorderSize())
Calculate the maximum window for a given tensor shape and border setting.
Definition: Helpers.cpp:28
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...
Definition: Helpers.inl:201
#define ARM_COMPUTE_ERROR_ON_MISMATCHING_SHAPES(...)
Definition: Validate.h:441
1 channel, 1 F16 per channel
virtual ValidRegion valid_region() const =0
Valid region of the tensor.
Implementation of a static rectangular access pattern.
bool update_window_and_padding(Window &win, Ts &&... patterns)
Update window and padding size for each of the access patterns.
Definition: Helpers.h:402
virtual const TensorShape & tensor_shape() const =0
Size for each dimension of the tensor.
Class to describe a number of elements in each dimension.
Definition: Steps.h:40
Implementation of a row access pattern.
virtual ITensorInfo * info() const =0
Interface to be implemented by the child class to return the tensor's metadata.
std::unique_ptr< Kernel > create_kernel()
Helper function to create and return a unique_ptr pointed to a CL/GLES kernel object.
Definition: Helpers.h:86
#define ARM_COMPUTE_ERROR_ON_DATA_TYPE_CHANNEL_NOT_IN(t, c,...)
Definition: Validate.h:789
static GCKernelLibrary & get()
Get the static instance of GCKernelLibrary.
#define ARM_COMPUTE_ERROR_ON_NULLPTR(...)
Definition: Validate.h:161
Describe a multidimensional execution window.
Definition: Window.h:39

References ARM_COMPUTE_ERROR_ON_DATA_TYPE_CHANNEL_NOT_IN, ARM_COMPUTE_ERROR_ON_MISMATCHING_DATA_TYPES, ARM_COMPUTE_ERROR_ON_MISMATCHING_SHAPES, ARM_COMPUTE_ERROR_ON_NULLPTR, arm_compute::auto_init_if_empty(), arm_compute::calculate_max_window(), arm_compute::create_kernel(), ITensorInfo::data_type(), arm_compute::F16, arm_compute::F32, GCKernelLibrary::get(), ITensor::info(), sum(), ITensorInfo::tensor_shape(), arm_compute::support::cpp11::to_string(), arm_compute::update_window_and_padding(), and ITensorInfo::valid_region().

Referenced by GCSoftmaxLayer::configure().

◆ operator=() [1/2]

GCLogits1DNormKernel& operator= ( const GCLogits1DNormKernel )
delete

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

◆ operator=() [2/2]

GCLogits1DNormKernel& operator= ( GCLogits1DNormKernel &&  )
default

Allow instances of this class to be moved.

◆ run()

void run ( const Window window)
overridevirtual

Enqueue the OpenGL ES shader to process the given window.

Parameters
[in]windowRegion on which to execute the kernel. (Must be a valid region of the window returned by window()).

Implements IGCKernel.

Definition at line 249 of file GCSoftmaxLayerKernel.cpp.

250 {
253 
255  Window slice = window_collapsed.first_slice_window_3D();
256 
257  _kernel.use();
258 
259  do
260  {
261  Window sum_slice = slice;
262  sum_slice.set(Window::DimX, Window::Dimension(0, 1, 1));
263 
264  unsigned int idx = 0;
265  unsigned int binding = 1; // SSBO binding starts from 1.
266  // Set inputs
267  add_3D_tensor_argument(idx, _input, binding++, slice);
268  add_3D_tensor_argument(idx, _sum, binding++, slice);
269  add_3D_tensor_argument(idx, _output, binding++, slice);
270 
271  _kernel.update_shader_params();
272  enqueue(*this, slice);
273  }
274  while(window_collapsed.slide_window_slice_3D(slice));
275 }
const Window & window() const
The maximum window the kernel can be executed on.
Definition: IKernel.cpp:28
void add_3D_tensor_argument(unsigned int &idx, const IGCTensor *tensor, const unsigned int binding_point, const Window &window)
Add the passed 3D tensor's parameters to the object's kernel's arguments starting from the index idx.
Definition: IGCKernel.cpp:132
void enqueue(cl::CommandQueue &queue, ICLKernel &kernel, const Window &window, const cl::NDRange &lws_hint=CLKernelLibrary::get().default_ndrange(), bool use_dummy_work_items=false)
Add the kernel to the command queue with the given window.
Definition: ICLKernel.cpp:39
Describe one of the image's dimensions with a start, end and step.
Definition: Window.h:75
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:54
void set(size_t dimension, const Dimension &dim)
Set the values of a given dimension.
Definition: Window.inl:48
bool slide_window_slice_3D(Window &slice) const
Slide the passed 3D window slice.
Definition: Window.h:319
static constexpr size_t DimZ
Alias for dimension 2 also known as Z dimension.
Definition: Window.h:47
Window first_slice_window_3D() const
First 3D slice of the window.
Definition: Window.h:275
#define ARM_COMPUTE_ERROR_ON_INVALID_SUBWINDOW(f, s)
Definition: Validate.h:205
Describe a multidimensional execution window.
Definition: Window.h:39
#define ARM_COMPUTE_ERROR_ON_UNCONFIGURED_KERNEL(k)
Definition: Validate.h:940
SimpleTensor< T > slice(const SimpleTensor< T > &src, Coordinates starts, Coordinates ends)

References IGCKernel::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(), Window::set(), arm_compute::test::validation::reference::slice(), Window::slide_window_slice_3D(), and IKernel::window().


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