Compute Library
 21.02
CpuPermuteKernel Class Reference

Kernel to perform tensor permutation given a permutation vector. More...

#include <CpuPermuteKernel.h>

Collaboration diagram for CpuPermuteKernel:
[legend]

Public Member Functions

 CpuPermuteKernel ()=default
 
 ARM_COMPUTE_DISALLOW_COPY_ALLOW_MOVE (CpuPermuteKernel)
 
void configure (const ITensorInfo *src, ITensorInfo *dst, const PermutationVector &perm)
 Configure kernel for a given list of arguments. More...
 
void run_op (ITensorPack &tensors, const Window &window, const ThreadInfo &info) override
 Execute the kernel on the passed window. More...
 
const char * name () const override
 Name of the kernel. More...
 
- Public Member Functions inherited from ICPPKernel
virtual ~ICPPKernel ()=default
 Default destructor. More...
 
virtual void run (const Window &window, const ThreadInfo &info)
 Execute the kernel on the passed window. More...
 
virtual void run_nd (const Window &window, const ThreadInfo &info, const Window &thread_locator)
 legacy compatibility layer for implemantions which do not support thread_locator In these cases we simply narrow the interface down the legacy version 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 *src, const ITensorInfo *dst, const PermutationVector &perm)
 Static function to check if given info will lead to a valid configuration of CpuPermuteKernel. More...
 

Detailed Description

Kernel to perform tensor permutation given a permutation vector.

Definition at line 37 of file CpuPermuteKernel.h.

Constructor & Destructor Documentation

◆ CpuPermuteKernel()

CpuPermuteKernel ( )
default

Member Function Documentation

◆ ARM_COMPUTE_DISALLOW_COPY_ALLOW_MOVE()

ARM_COMPUTE_DISALLOW_COPY_ALLOW_MOVE ( CpuPermuteKernel  )

◆ configure()

void configure ( const ITensorInfo src,
ITensorInfo dst,
const PermutationVector perm 
)

Configure kernel for a given list of arguments.

Note
Arbitrary permutation vectors are supported with rank not greater than 4
Parameters
[in]srcSrouce tensor to permute. Data types supported: All
[out]dstDestination tensor. Data types supported: Same as src
[in]permPermutation vector

Definition at line 243 of file CpuPermuteKernel.cpp.

References ARM_COMPUTE_ERROR_ON_NULLPTR, ARM_COMPUTE_ERROR_THROW_ON, arm_compute::auto_init_if_empty(), arm_compute::calculate_max_window(), ICloneable< T >::clone(), arm_compute::misc::shape_calculator::compute_permutation_output_shape(), arm_compute::test::validation::dst_shape, ITensorInfo::num_dimensions(), Dimensions< T >::set_num_dimensions(), ITensorInfo::set_valid_region(), ITensorInfo::tensor_shape(), and arm_compute::validate_arguments().

244 {
247  // Destination auto inizialitation if not yet initialized
248  auto_init_if_empty(*dst, src->clone()->set_tensor_shape(dst_shape));
249 
250  // Perform validation step
252 
253  _perm = perm;
254 
255  // Configure kernel window
256  Window win = calculate_max_window(*src, Steps());
257 
258  // The NEPermute doesn't need padding so update_window_and_padding() can be skipped
259  Coordinates coord;
260  coord.set_num_dimensions(dst->num_dimensions());
261  dst->set_valid_region(ValidRegion(coord, dst->tensor_shape()));
262 
263  ICpuKernel::configure(win);
264 }
Window calculate_max_window(const ValidRegion &valid_region, const Steps &steps, bool skip_border, BorderSize border_size)
TensorShape compute_permutation_output_shape(const ITensorInfo &input, const PermutationVector &perm)
Calculate the permuted shape of an input given a permutation vector.
#define ARM_COMPUTE_ERROR_THROW_ON(status)
Definition: Error.h:455
SimpleTensor< float > src
Definition: DFT.cpp:155
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...
Status validate_arguments(const ITensorInfo *input, const ITensorInfo *bias, const ITensorInfo *output, const GEMMLowpOutputStageInfo *output_stage)
#define ARM_COMPUTE_ERROR_ON_NULLPTR(...)
Definition: Validate.h:161

◆ name()

const char * name ( ) const
overridevirtual

Name of the kernel.

Returns
Kernel name

Implements ICPPKernel.

Definition at line 298 of file CpuPermuteKernel.cpp.

299 {
300  return "CpuPermuteKernel";
301 }

◆ run_op()

void run_op ( ITensorPack tensors,
const Window window,
const ThreadInfo info 
)
overridevirtual

Execute the kernel on the passed window.

Warning
If is_parallelisable() returns false then the passed window must be equal to window()
Note
The window has to be a region within the window returned by the window() method
The width of the window has to be a multiple of num_elems_processed_per_iteration().
Parameters
[in]tensorsA vector containing the tensors to operate on.
[in]windowRegion on which to execute the kernel. (Must be a region of the window returned by window())
[in]infoInfo about executing thread and CPU.

Reimplemented from ICPPKernel.

Definition at line 272 of file CpuPermuteKernel.cpp.

References arm_compute::ACL_DST, arm_compute::ACL_SRC, ARM_COMPUTE_ERROR, ARM_COMPUTE_ERROR_ON_INVALID_SUBWINDOW, ARM_COMPUTE_ERROR_ON_UNCONFIGURED_KERNEL, ARM_COMPUTE_UNUSED, arm_compute::test::validation::dst, ITensorPack::get_const_tensor(), ITensorPack::get_tensor(), arm_compute::test::validation::src, and IKernel::window().

273 {
277 
278  const auto src = tensors.get_const_tensor(TensorType::ACL_SRC);
279  auto dst = tensors.get_tensor(TensorType::ACL_DST);
280 
281  switch(src->info()->element_size())
282  {
283  case 1:
284  run_permute<uint8_t>(window, src, dst, _perm);
285  break;
286  case 2:
287  run_permute<uint16_t>(window, src, dst, _perm);
288  break;
289  case 4:
290  run_permute<uint32_t>(window, src, dst, _perm);
291  break;
292  default:
293  ARM_COMPUTE_ERROR("Element size not supported");
294  break;
295  }
296 }
const Window & window() const
The maximum window the kernel can be executed on.
Definition: IKernel.cpp:28
#define ARM_COMPUTE_ERROR(msg)
Print the given message then throw an std::runtime_error.
Definition: Error.h:352
SimpleTensor< float > src
Definition: DFT.cpp:155
#define ARM_COMPUTE_UNUSED(...)
To avoid unused variables warnings.
Definition: Error.h:152
#define ARM_COMPUTE_ERROR_ON_UNCONFIGURED_KERNEL(k)
Definition: Validate.h:941
ScaleKernelInfo info(interpolation_policy, default_border_mode, PixelValue(), sampling_policy, false)
#define ARM_COMPUTE_ERROR_ON_INVALID_SUBWINDOW(f, s)
Definition: Validate.h:205

◆ validate()

Status validate ( const ITensorInfo src,
const ITensorInfo dst,
const PermutationVector perm 
)
static

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

Note
Arbitrary permutation vectors are supported with rank not greater than 4
Parameters
[in]srcSource tensor to permute. Data types supported: All
[in]dstDestination tensor. Data types supported: Same as src
[in]permPermutation vector
Returns
a status

Definition at line 266 of file CpuPermuteKernel.cpp.

References ARM_COMPUTE_RETURN_ON_ERROR, and arm_compute::validate_arguments().

Referenced by CpuPermute::validate().

267 {
269  return Status{};
270 }
#define ARM_COMPUTE_RETURN_ON_ERROR(status)
Checks if a status contains an error and returns it.
Definition: Error.h:204
SimpleTensor< float > src
Definition: DFT.cpp:155
Status validate_arguments(const ITensorInfo *input, const ITensorInfo *bias, const ITensorInfo *output, const GEMMLowpOutputStageInfo *output_stage)

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