Compute Library
 23.05
ClWidthConcatenate4TensorsKernel Class Reference

Interface for the width concatenate kernel of 4 tensors. More...

#include <ClWidthConcatenate4TensorsKernel.h>

Collaboration diagram for ClWidthConcatenate4TensorsKernel:
[legend]

Public Member Functions

 ClWidthConcatenate4TensorsKernel ()
 
 ARM_COMPUTE_DISALLOW_COPY_ALLOW_MOVE (ClWidthConcatenate4TensorsKernel)
 
void configure (const CLCompileContext &compile_context, ITensorInfo *src1, ITensorInfo *src2, ITensorInfo *src3, ITensorInfo *src4, ITensorInfo *dst)
 Initialise the kernel's sources and destination. More...
 
void run_op (ITensorPack &tensors, const Window &window, ::cl::CommandQueue &queue) override
 
- 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...
 
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...
 
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 Windowwindow () 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 *src1, const ITensorInfo *src2, const ITensorInfo *src3, const ITensorInfo *src4, const ITensorInfo *dst)
 Static function to check if given info will lead to a valid configuration. More...
 
- Static Public Member Functions inherited from ICLKernel
static constexpr unsigned int num_arguments_per_3d_tensor_nhw ()
 Returns the number of arguments enqueued per NHW 3D Tensor object. More...
 
static constexpr unsigned int num_arguments_per_4d_tensor_nhwc ()
 Returns the number of arguments enqueued per NHWC 4D Tensor object. More...
 
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, bool use_dummy_work_items)
 Get the global work size given an execution window. More...
 

Detailed Description

Interface for the width concatenate kernel of 4 tensors.

All source tensors will be concatenated into the destination tensor.

Definition at line 41 of file ClWidthConcatenate4TensorsKernel.h.

Constructor & Destructor Documentation

◆ ClWidthConcatenate4TensorsKernel()

Definition at line 67 of file ClWidthConcatenate4TensorsKernel.cpp.

References arm_compute::ELEMENTWISE.

68 {
70 }
Elementwise CL kernel type.
Definition: CLTypes.h:85

Member Function Documentation

◆ ARM_COMPUTE_DISALLOW_COPY_ALLOW_MOVE()

ARM_COMPUTE_DISALLOW_COPY_ALLOW_MOVE ( ClWidthConcatenate4TensorsKernel  )

◆ configure()

void configure ( const CLCompileContext compile_context,
ITensorInfo src1,
ITensorInfo src2,
ITensorInfo src3,
ITensorInfo src4,
ITensorInfo dst 
)

Initialise the kernel's sources and destination.

Parameters
[in]compile_contextThe compile context to be used.
[in]src1First source tensor info. Data types supported: All.
[in]src2Second source tensor info. Data types supported: same as src1
[in]src3Third source tensor info. Data types supported: same as src1
[in]src4Fourth source tensor info. Data types supported: same as src1
[out]dstDestination tensor info. Data types supported: same as src1.

Definition at line 78 of file ClWidthConcatenate4TensorsKernel.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::calculate_max_window(), arm_compute::create_kernel(), ITensorInfo::data_type(), ITensorInfo::dimension(), Window::DimZ, ITensorInfo::element_size(), arm_compute::float_to_string_with_full_precision(), arm_compute::get_cl_type_from_data_type(), arm_compute::get_padding_info(), arm_compute::has_padding_changed(), arm_compute::is_data_type_quantized_asymmetric(), kernel_name, arm_compute::lower_string(), num_elems_processed_per_iteration, UniformQuantizationInfo::offset, CLBuildOptions::options(), ITensorInfo::quantization_info(), UniformQuantizationInfo::scale, arm_compute::string_from_data_type(), arm_compute::helpers::tensor_info::tensors_have_different_quantization_info(), arm_compute::support::cpp11::to_string(), QuantizationInfo::uniform(), arm_compute::upper_string(), and arm_compute::cpu::kernels::validate_arguments().

82 {
83  ARM_COMPUTE_ERROR_ON_NULLPTR(src1, src2, src3, src4, dst);
84  ARM_COMPUTE_ERROR_THROW_ON(validate_arguments(src1, src2, src3, src4, dst));
85 
86  auto padding_info = get_padding_info({ src1, src2, src3, src4, dst });
87  const unsigned int min_dimension = std::min(std::min(src1->dimension(0), src2->dimension(0)), std::min(src3->dimension(0), src4->dimension(0)));
88  const unsigned int num_elems_processed_per_iteration = adjust_vec_size(8, min_dimension);
89  const unsigned int vec_size_leftover = dst->dimension(0) % num_elems_processed_per_iteration;
90 
91  // Add build options
92  CLBuildOptions build_opts;
93  build_opts.add_option("-DDATA_TYPE=" + get_cl_type_from_data_type(src1->data_type()));
94  build_opts.add_option("-DVEC_SIZE=" + support::cpp11::to_string(num_elems_processed_per_iteration));
95  build_opts.add_option("-DVEC_SIZE_LEFTOVER=" + support::cpp11::to_string(vec_size_leftover));
96  build_opts.add_option("-DELEMENT_SIZE=" + support::cpp11::to_string(src1->element_size()));
97  build_opts.add_option("-DINPUT1_ROTATE_N=" + support::cpp11::to_string((src1->dimension(0) - vec_size_leftover) % num_elems_processed_per_iteration));
98  build_opts.add_option("-DINPUT2_ROTATE_N=" + support::cpp11::to_string((src1->dimension(0) + src2->dimension(0) - vec_size_leftover) % num_elems_processed_per_iteration));
99  build_opts.add_option("-DINPUT3_ROTATE_N=" + support::cpp11::to_string((src1->dimension(0) + src2->dimension(0) + src3->dimension(0) - vec_size_leftover) % num_elems_processed_per_iteration));
100 
101  _depth = src1->dimension(2);
102  _input1_width = src1->dimension(0);
103  _input2_width = src2->dimension(0);
104  _input3_width = src3->dimension(0);
105 
106  // If soources have different quantization info set quantization parameters needed for the re-quantization process
107  const bool have_different_qinfo = helpers::tensor_info::tensors_have_different_quantization_info(dst, src1, src2, src3, src4);
108  if(is_data_type_quantized_asymmetric(src1->data_type()) && have_different_qinfo)
109  {
110  const UniformQuantizationInfo iq1_info = src1->quantization_info().uniform();
111  const UniformQuantizationInfo iq2_info = src2->quantization_info().uniform();
112  const UniformQuantizationInfo iq3_info = src3->quantization_info().uniform();
113  const UniformQuantizationInfo iq4_info = src4->quantization_info().uniform();
114  const UniformQuantizationInfo oq_info = dst->quantization_info().uniform();
115 
116  build_opts.add_option("-DOFFSET_IN1=" + float_to_string_with_full_precision(iq1_info.offset));
117  build_opts.add_option("-DSCALE_IN1=" + float_to_string_with_full_precision(iq1_info.scale));
118  build_opts.add_option("-DOFFSET_IN2=" + float_to_string_with_full_precision(iq2_info.offset));
119  build_opts.add_option("-DSCALE_IN2=" + float_to_string_with_full_precision(iq2_info.scale));
120  build_opts.add_option("-DOFFSET_IN3=" + float_to_string_with_full_precision(iq3_info.offset));
121  build_opts.add_option("-DSCALE_IN3=" + float_to_string_with_full_precision(iq3_info.scale));
122  build_opts.add_option("-DOFFSET_IN4=" + float_to_string_with_full_precision(iq4_info.offset));
123  build_opts.add_option("-DSCALE_IN4=" + float_to_string_with_full_precision(iq4_info.scale));
124  build_opts.add_option("-DOFFSET_OUT=" + float_to_string_with_full_precision(oq_info.offset));
125  build_opts.add_option("-DSCALE_OUT=" + float_to_string_with_full_precision(oq_info.scale));
126  }
127  std::string kernel_name = "concatenate_width_x4";
128 
129  // A macro guard to compile ONLY the kernel of interest
130  build_opts.add_option("-D" + upper_string(kernel_name));
131 
132  // Create kernel
133  _kernel = create_kernel(compile_context, kernel_name, build_opts.options());
134 
135  // Configure kernel window
136  Window win = calculate_max_window(*dst, Steps(num_elems_processed_per_iteration));
137  ICLKernel::configure_internal(win.collapse(win, Window::DimZ));
138 
140 
141  // Set config_id for enabling LWS tuning
142  _config_id = "concatenate_width_x4_";
143  _config_id += lower_string(string_from_data_type(src1->data_type()));
144  _config_id += "_";
145  _config_id += support::cpp11::to_string(src1->dimension(0));
146  _config_id += "_";
147  _config_id += support::cpp11::to_string(src1->dimension(1));
148  _config_id += "_";
149  _config_id += support::cpp11::to_string(src2->dimension(0));
150  _config_id += "_";
151  _config_id += support::cpp11::to_string(src2->dimension(1));
152  _config_id += "_";
153  _config_id += support::cpp11::to_string(src3->dimension(0));
154  _config_id += "_";
155  _config_id += support::cpp11::to_string(src3->dimension(1));
156  _config_id += "_";
157  _config_id += support::cpp11::to_string(src4->dimension(0));
158  _config_id += "_";
159  _config_id += support::cpp11::to_string(src4->dimension(1));
160 }
Window calculate_max_window(const ValidRegion &valid_region, const Steps &steps, bool skip_border, BorderSize border_size)
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
#define ARM_COMPUTE_ERROR_THROW_ON(status)
Definition: Error.h:455
std::string lower_string(const std::string &val)
Lower a given string.
Definition: Utils.cpp:353
Status validate_arguments(const ITensorInfo *src, const ITensorInfo *weights, const ITensorInfo *dst, const PadStrideInfo &conv_info)
std::string upper_string(const std::string &val)
Raise a given string to upper case.
Definition: Utils.cpp:360
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:404
const std::string & string_from_data_type(DataType dt)
Convert a data type identity into a string.
Definition: Utils.cpp:135
std::string float_to_string_with_full_precision(float val)
Create a string with the float in full precision.
Definition: Utils.h:1124
unsigned int num_elems_processed_per_iteration
std::string get_cl_type_from_data_type(const DataType &dt)
Translates a tensor data type to the appropriate OpenCL type.
Definition: CLHelpers.cpp:39
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:603
bool is_data_type_quantized_asymmetric(DataType dt)
Check if a given data type is of asymmetric quantized type.
Definition: Utils.h:1052
bool tensors_have_different_quantization_info(const ITensorInfo *tensor_info_1, const ITensorInfo *tensor_info_2, Ts... tensor_infos)
Checks if the quantization info of given tensors are different.
Definition: tensor_info.h:44
static constexpr size_t DimZ
Alias for dimension 2 also known as Z dimension.
Definition: Window.h:47
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:588
#define ARM_COMPUTE_ERROR_ON_NULLPTR(...)
Definition: Validate.h:157
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:1222
std::string kernel_name

◆ run_op()

void run_op ( ITensorPack tensors,
const Window window,
::cl::CommandQueue &  queue 
)
override

Definition at line 162 of file ClWidthConcatenate4TensorsKernel.cpp.

References arm_compute::ACL_DST, arm_compute::ACL_SRC_VEC, ICLKernel::add_4D_tensor_argument(), ARM_COMPUTE_ERROR_ON_INVALID_SUBWINDOW, ARM_COMPUTE_ERROR_ON_UNCONFIGURED_KERNEL, arm_compute::enqueue(), Window::first_slice_window_4D(), ITensorPack::get_const_tensor(), ITensorPack::get_tensor(), ICLKernel::lws_hint(), arm_compute::test::validation::reference::slice(), Window::slide_window_slice_4D(), and IKernel::window().

163 {
166 
167  const auto src0 = utils::cast::polymorphic_downcast<const ICLTensor *>(tensors.get_const_tensor(TensorType::ACL_SRC_VEC));
168  const auto src1 = utils::cast::polymorphic_downcast<const ICLTensor *>(tensors.get_const_tensor(TensorType::ACL_SRC_VEC + 1));
169  const auto src2 = utils::cast::polymorphic_downcast<const ICLTensor *>(tensors.get_const_tensor(TensorType::ACL_SRC_VEC + 2));
170  const auto src3 = utils::cast::polymorphic_downcast<const ICLTensor *>(tensors.get_const_tensor(TensorType::ACL_SRC_VEC + 3));
171  auto dst = utils::cast::polymorphic_downcast<ICLTensor *>(tensors.get_tensor(TensorType::ACL_DST));
172 
174 
175  do
176  {
177  unsigned int idx = 0;
178  add_4D_tensor_argument(idx, src0, slice);
179  add_4D_tensor_argument(idx, src1, slice);
180  add_4D_tensor_argument(idx, src2, slice);
181  add_4D_tensor_argument(idx, src3, slice);
182  add_4D_tensor_argument(idx, dst, slice);
183  _kernel.setArg<cl_int>(idx++, _depth);
184  _kernel.setArg<cl_int>(idx++, _input1_width);
185  _kernel.setArg<cl_int>(idx++, _input2_width);
186  _kernel.setArg<cl_int>(idx++, _input3_width);
187  enqueue(queue, *this, window, lws_hint());
188  }
189  while(window.slide_window_slice_4D(slice));
190 }
const Window & window() const
The maximum window the kernel can be executed on.
Definition: IKernel.cpp:28
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:32
cl::NDRange lws_hint() const
Return the Local-Workgroup-Size hint.
Definition: ICLKernel.h:371
#define ARM_COMPUTE_ERROR_ON_UNCONFIGURED_KERNEL(k)
Definition: Validate.h:915
Window first_slice_window_4D() const
First 4D slice of the window.
Definition: Window.h:313
bool slide_window_slice_4D(Window &slice) const
Slide the passed 4D window slice.
Definition: Window.h:361
void add_4D_tensor_argument(unsigned int &idx, const ICLTensor *tensor, const Window &window)
Add the passed 4D tensor&#39;s parameters to the object&#39;s kernel&#39;s arguments starting from the index idx...
Definition: ICLKernel.h:232
#define ARM_COMPUTE_ERROR_ON_INVALID_SUBWINDOW(f, s)
Definition: Validate.h:201
SimpleTensor< T > slice(const SimpleTensor< T > &src, Coordinates starts, Coordinates ends)

◆ validate()

Status validate ( const ITensorInfo src1,
const ITensorInfo src2,
const ITensorInfo src3,
const ITensorInfo src4,
const ITensorInfo dst 
)
static

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

Similar to ClWidthConcatenate4TensorsKernel::configure()

Returns
a status

Definition at line 72 of file ClWidthConcatenate4TensorsKernel.cpp.

References ARM_COMPUTE_RETURN_ON_ERROR, and arm_compute::cpu::kernels::validate_arguments().

Referenced by ClConcatenate::validate().

73 {
74  ARM_COMPUTE_RETURN_ON_ERROR(validate_arguments(src1, src2, src3, src4, dst));
75  return Status{};
76 }
#define ARM_COMPUTE_RETURN_ON_ERROR(status)
Checks if a status contains an error and returns it.
Definition: Error.h:204
Status validate_arguments(const ITensorInfo *src, const ITensorInfo *weights, const ITensorInfo *dst, const PadStrideInfo &conv_info)

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