Compute Library
 19.08
GCCol2ImKernel Class Reference

Interface for the col2im reshaping kernel. More...

#include <GCCol2ImKernel.h>

Collaboration diagram for GCCol2ImKernel:
[legend]

Public Member Functions

 GCCol2ImKernel ()
 Default constructor. More...
 
 GCCol2ImKernel (const GCCol2ImKernel &)=delete
 Prevent instances of this class from being copied (As this class contains pointers) More...
 
GCCol2ImKerneloperator= (const GCCol2ImKernel &)=delete
 Prevent instances of this class from being copied (As this class contains pointers) More...
 
 GCCol2ImKernel (GCCol2ImKernel &&)=default
 Allow instances of this class to be moved. More...
 
GCCol2ImKerneloperator= (GCCol2ImKernel &&)=default
 Allow instances of this class to be moved. More...
 
 ~GCCol2ImKernel ()=default
 Default destructor. More...
 
void configure (const IGCTensor *input, IGCTensor *output, std::pair< unsigned int, unsigned int > convolved_dims)
 Set the input and output of the kernel. 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 the col2im reshaping kernel.

Rearranges each matrix column into image blocks. It's the inverse operation of GCIm2ColKernel.

For example, a vector of 9 elements can be reshaped to a block(image) of 3x3:

\[ \left( \begin{array}{ccccccccc} a0 & a1 & a2 & a3 & a4 & a5 & a6 & a7 & a8 \\ \end{array} \right) \rightarrow \left( \begin{array}{ccc} a0 & a1 & a2 \\ a3 & a4 & a5 \\ a6 & a7 & a8 \\ \end{array} \right) \]

Definition at line 52 of file GCCol2ImKernel.h.

Constructor & Destructor Documentation

◆ GCCol2ImKernel() [1/3]

Default constructor.

Definition at line 39 of file GCCol2ImKernel.cpp.

40  : _input(nullptr), _output(nullptr), _convolved_dims()
41 {
42 }

◆ GCCol2ImKernel() [2/3]

GCCol2ImKernel ( const GCCol2ImKernel )
delete

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

◆ GCCol2ImKernel() [3/3]

GCCol2ImKernel ( GCCol2ImKernel &&  )
default

Allow instances of this class to be moved.

◆ ~GCCol2ImKernel()

~GCCol2ImKernel ( )
default

Default destructor.

Member Function Documentation

◆ configure()

void configure ( const IGCTensor input,
IGCTensor output,
std::pair< unsigned int, unsigned int >  convolved_dims 
)

Set the input and output of the kernel.

Parameters
[in]inputThe input tensor to convert. Data types supported: F16/F32
[out]outputThe output tensor. 3 lower dimensions represent a single output [width, height, OFM], while the rest represent batch of outputs. Data types supported: Same as input
[in]convolved_dimsOutput convolved dimensions.

Definition at line 44 of file GCCol2ImKernel.cpp.

46 {
49 
51  output_shape.set(0, convolved_dims.first);
52  output_shape.set(1, convolved_dims.second);
53  output_shape.set(2, input->info()->tensor_shape()[0]);
54 
55  // Output auto inizialitation if not yet initialized
56  auto_init_if_empty(*output->info(), input->info()->clone()->set_tensor_shape(output_shape));
57 
60 
61  _input = input;
62  _output = output;
63  _convolved_dims = convolved_dims;
64 
65  const DataType dt = input->info()->data_type();
66  const unsigned int local_size = 1;
67 
68  // Create kernel
69  std::set<std::string> build_opts;
70  build_opts.emplace("#define COL2IM ");
71  build_opts.emplace("#define WIDTH_OUTPUT " + support::cpp11::to_string(_convolved_dims.first));
72  const std::string dt_name = (dt == DataType::F32) ? "DATA_TYPE_FP32" : "DATA_TYPE_FP16";
73  build_opts.emplace(("#define " + dt_name));
74  build_opts.emplace("#define LOCAL_SIZE_X " + support::cpp11::to_string(local_size));
75  build_opts.emplace("#define LOCAL_SIZE_Y " + support::cpp11::to_string(local_size));
76  build_opts.emplace("#define LOCAL_SIZE_Z " + support::cpp11::to_string(local_size));
77 
78  _kernel = static_cast<GCKernel>(GCKernelLibrary::get().create_kernel("col2im", build_opts));
79 
80  // Configure window
81  const unsigned int num_elems_processed_per_iteration = (dt == DataType::F32) ? 1 : 2;
82 
83  Window win = calculate_max_window(*output->info(), Steps(num_elems_processed_per_iteration));
84 
85  AccessWindowHorizontal output_access(output->info(), 0, num_elems_processed_per_iteration);
86  const int input_padding = ceil_to_multiple(input->info()->dimension(0), 2) - input->info()->dimension(0);
87 
88  AccessWindowStatic input_access(input->info(), 0, 0, input->info()->dimension(0) + input_padding, input->info()->dimension(1) + 1);
89 
90  update_window_and_padding(win, input_access, output_access);
91 
92  output_access.set_valid_region(win, output->info()->valid_region());
93 
94  IGCKernel::configure(win);
95 }
Shape of a tensor.
Definition: TensorShape.h:39
virtual size_t dimension(size_t index) const =0
Return the size of the requested dimension.
#define ARM_COMPUTE_ERROR_ON_MISMATCHING_DATA_TYPES(...)
Definition: Validate.h:543
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
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.
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:66
Class to describe a number of elements in each dimension.
Definition: Steps.h:40
Implementation of a row access pattern.
virtual std::unique_ptr< T > clone() const =0
Provide a clone of the current object of class T.
virtual ITensorInfo * info() const =0
Interface to be implemented by the child class to return the tensor's metadata.
#define ARM_COMPUTE_ERROR_ON_MISMATCHING_DIMENSIONS(...)
Definition: Validate.h:286
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
DataType
Available data types.
Definition: Types.h:74
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_DIMENSIONS, ARM_COMPUTE_ERROR_ON_NULLPTR, arm_compute::auto_init_if_empty(), arm_compute::calculate_max_window(), arm_compute::ceil_to_multiple(), ICloneable< T >::clone(), arm_compute::create_kernel(), ITensorInfo::data_type(), ITensorInfo::dimension(), arm_compute::F16, arm_compute::F32, GCKernelLibrary::get(), ITensor::info(), arm_compute::test::validation::output_shape, ITensorInfo::tensor_shape(), arm_compute::support::cpp11::to_string(), arm_compute::update_window_and_padding(), and ITensorInfo::valid_region().

Referenced by GCConvolutionLayer::configure().

◆ operator=() [1/2]

GCCol2ImKernel& operator= ( const GCCol2ImKernel )
delete

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

◆ operator=() [2/2]

GCCol2ImKernel& operator= ( GCCol2ImKernel &&  )
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 97 of file GCCol2ImKernel.cpp.

98 {
101 
102  _kernel.use();
103 
105  Window slice = collapsed_window.first_slice_window_3D();
106 
107  // Set static kernel arguments
108  unsigned int idx = 2 * num_arguments_per_3D_tensor();
109  //_kernel.set_argument(idx++, _output->info()->strides_in_bytes()[3]);
110  _kernel.set_argument(idx++, uint(_output->info()->dimension(2)));
111  _kernel.set_argument(idx++, _input->info()->strides_in_bytes()[2]);
112 
113  do
114  {
115  // Set inputs
116  unsigned int idx = 0;
117  add_2D_tensor_argument(idx, _input, 1, slice);
118  add_3D_tensor_argument(idx, _output, 2, slice);
119  _kernel.update_shader_params();
120  enqueue(*this, slice);
121  }
122  while(collapsed_window.slide_window_slice_3D(slice));
123 }
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
virtual size_t dimension(size_t index) const =0
Return the size of the requested dimension.
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
unsigned int num_arguments_per_3D_tensor() const
Returns the number of arguments enqueued per 3D tensor object.
Definition: IGCKernel.cpp:147
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
virtual ITensorInfo * info() const =0
Interface to be implemented by the child class to return the tensor's metadata.
#define ARM_COMPUTE_ERROR_ON_MISMATCHING_WINDOWS(f, w)
Definition: Validate.h:183
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.
Definition: IGCKernel.cpp:127
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
virtual const Strides & strides_in_bytes() const =0
The strides in bytes for accessing each dimension of the tensor.
Window first_slice_window_3D() const
First 3D slice of the window.
Definition: Window.h:275
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_2D_tensor_argument(), IGCKernel::add_3D_tensor_argument(), ARM_COMPUTE_ERROR_ON_MISMATCHING_WINDOWS, ARM_COMPUTE_ERROR_ON_UNCONFIGURED_KERNEL, Window::collapse_if_possible(), ITensorInfo::dimension(), Window::DimZ, arm_compute::enqueue(), Window::first_slice_window_3D(), ITensor::info(), IGCKernel::num_arguments_per_3D_tensor(), arm_compute::test::validation::reference::slice(), Window::slide_window_slice_3D(), ITensorInfo::strides_in_bytes(), and IKernel::window().


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