Compute Library
 21.02
GCLogits1DMaxKernel Class Reference

Interface for the identifying the max value of 1D Logits. More...

#include <GCSoftmaxLayerKernel.h>

Collaboration diagram for GCLogits1DMaxKernel:
[legend]

Public Member Functions

void configure (const IGCTensor *input, IGCTensor *output)
 Set the input and output tensors. More...
 
- Public Member Functions inherited from IGCSimple3DKernel
void run (const Window &window) override
 Enqueue the OpenGL ES shader to process the given window. More...
 
- Public Member Functions inherited from IGCSimpleKernel
 IGCSimpleKernel ()
 Constructor. More...
 
 IGCSimpleKernel (const IGCSimpleKernel &)=delete
 Prevent instances of this class from being copied (As this class contains pointers) More...
 
IGCSimpleKerneloperator= (const IGCSimpleKernel &)=delete
 Prevent instances of this class from being copied (As this class contains pointers) More...
 
 IGCSimpleKernel (IGCSimpleKernel &&)=default
 Allow instances of this class to be moved. More...
 
IGCSimpleKerneloperator= (IGCSimpleKernel &&)=default
 Allow instances of this class to be moved. More...
 
 ~IGCSimpleKernel ()=default
 Default destructor. More...
 
void configure (const IGCTensor *input, IGCTensor *output, unsigned int num_elems_processed_per_iteration, bool border_undefined=false, const BorderSize &border_size=BorderSize())
 Configure the kernel. 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 the identifying the max value of 1D Logits.

Definition at line 34 of file GCSoftmaxLayerKernel.h.

Member Function Documentation

◆ configure()

void configure ( const IGCTensor input,
IGCTensor output 
)

Set the input and output tensors.

Parameters
[in]inputSource tensor. Data types supported: F16/F32
[out]outputDestination tensor. Data types supported: same as input

Definition at line 45 of file GCSoftmaxLayerKernel.cpp.

References ARM_COMPUTE_ERROR_ON_DATA_TYPE_CHANNEL_NOT_IN, ARM_COMPUTE_ERROR_ON_MISMATCHING_DATA_TYPES, ARM_COMPUTE_ERROR_ON_MISMATCHING_DIMENSIONS, ARM_COMPUTE_ERROR_ON_NULLPTR, arm_compute::auto_init_if_empty(), arm_compute::calculate_max_window(), arm_compute::ceil_to_multiple(), GCKernelLibrary::create_kernel(), ITensorInfo::data_type(), ITensorInfo::dimension(), arm_compute::F16, arm_compute::F32, GCKernelLibrary::get(), ITensor::info(), arm_compute::test::validation::input, IGCKernel::num_arguments_per_3D_tensor(), num_elems_processed_per_iteration, arm_compute::test::validation::output_shape, TensorShape::set(), ITensorInfo::tensor_shape(), arm_compute::support::cpp11::to_string(), and arm_compute::update_window_and_padding().

Referenced by GCSoftmaxLayer::configure().

46 {
49 
50  // Softmax across the x dimension
52  output_shape.set(0, 1);
53 
54  // Output auto initialization if not yet initialized
55  auto_init_if_empty(*output->info(), output_shape, 1, input->info()->data_type());
56 
59 
60  _input = input;
61  _output = output;
62 
63  // Set build options
64  std::set<std::string> build_opts;
65  std::string dt_name = (input->info()->data_type() == DataType::F32) ? "DATA_TYPE_FP32" : "DATA_TYPE_FP16";
66  build_opts.insert("#define " + dt_name);
67  build_opts.emplace("#define LOCAL_SIZE_X " + support::cpp11::to_string(1));
68  build_opts.emplace("#define LOCAL_SIZE_Y " + support::cpp11::to_string(1));
69  build_opts.emplace("#define LOCAL_SIZE_Z " + support::cpp11::to_string(1));
70  build_opts.insert("#define SOFTMAX_LAYER_MAX");
71 
72  // Tell the kernel that the width is not a multiple of 8
73  if((input->info()->dimension(0) % 8) != 0)
74  {
75  build_opts.insert("#define NON_MULTIPLE_OF_8");
76  }
77 
78  // Create kernel
79  _kernel = static_cast<GCKernel>(GCKernelLibrary::get().create_kernel("softmax_layer_max", build_opts));
80 
81  // Set fixed arguments
82  unsigned int idx = 2 * num_arguments_per_3D_tensor(); //Skip the input and output parameters
83  _kernel.set_argument(idx++, input->info()->dimension(0));
84 
85  // Configure kernel window
86  // The kernel loops over all elements in steps of 8
87  const unsigned int num_elems_processed_per_iteration = ceil_to_multiple(input->info()->dimension(0), 8);
88  unsigned int num_elems_written_per_iteration = 1;
89  if(input->info()->data_type() == DataType::F16)
90  {
91  num_elems_written_per_iteration = 2;
92  }
93 
94  Window win = calculate_max_window(*input->info(), Steps(num_elems_processed_per_iteration));
96  AccessWindowHorizontal output_access(output->info(), 0, num_elems_written_per_iteration);
97 
98  update_window_and_padding(win, input_access, output_access);
99 
100  output_access.set_valid_region(win, ValidRegion(Coordinates(), output->info()->tensor_shape()));
101 
102  IGCKernel::configure(win);
103 }
Window calculate_max_window(const ValidRegion &valid_region, const Steps &steps, bool skip_border, BorderSize border_size)
Shape of a tensor.
Definition: TensorShape.h:39
virtual size_t dimension(size_t index) const =0
Return the size of the requested dimension.
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
GCKernel class.
unsigned int num_arguments_per_3D_tensor() const
Returns the number of arguments enqueued per 3D tensor object.
Definition: IGCKernel.cpp:147
1 channel, 1 F16 per channel
bool update_window_and_padding(Window &win, Ts &&... patterns)
Update window and padding size for each of the access patterns.
Definition: WindowHelpers.h:46
virtual const TensorShape & tensor_shape() const =0
Size for each dimension of the tensor.
#define ARM_COMPUTE_ERROR_ON_MISMATCHING_DATA_TYPES(...)
Definition: Validate.h:543
auto ceil_to_multiple(S value, T divisor) -> decltype(((value+divisor - 1)/divisor) *divisor)
Computes the smallest number larger or equal to value that is a multiple of divisor.
Definition: Utils.h:71
Class to describe a number of elements in each dimension.
Definition: Steps.h:40
Coordinates of an item.
Definition: Coordinates.h:37
Implementation of a row access pattern.
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...
virtual ITensorInfo * info() const =0
Interface to be implemented by the child class to return the tensor&#39;s metadata.
#define ARM_COMPUTE_ERROR_ON_DATA_TYPE_CHANNEL_NOT_IN(t, c,...)
Definition: Validate.h:790
static GCKernelLibrary & get()
Get the static instance of GCKernelLibrary.
#define ARM_COMPUTE_ERROR_ON_MISMATCHING_DIMENSIONS(...)
Definition: Validate.h:286
GCKernel create_kernel(const std::string &shader_name, const StringSet &build_options_set={}) const
Creates a kernel from the kernel library.
unsigned int num_elems_processed_per_iteration
#define ARM_COMPUTE_ERROR_ON_NULLPTR(...)
Definition: Validate.h:161
Container for valid region of a window.
Definition: Types.h:188
Describe a multidimensional execution window.
Definition: Window.h:39
TensorShape & set(size_t dimension, size_t value, bool apply_dim_correction=true, bool increase_dim_unit=true)
Accessor to set the value of one of the dimensions.
Definition: TensorShape.h:79

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