Compute Library
 19.11
CLGEMMLowpMatrixMultiplyReshapedOnlyRHSKernel Class Reference

OpenCL kernel to multiply matrices with QASYMM8 data type when only the input matrix RHS (input1) has been reshaped. More...

#include <CLGEMMLowpMatrixMultiplyReshapedOnlyRHSKernel.h>

Collaboration diagram for CLGEMMLowpMatrixMultiplyReshapedOnlyRHSKernel:
[legend]

Public Member Functions

 CLGEMMLowpMatrixMultiplyReshapedOnlyRHSKernel ()
 Default Constructor. More...
 
 CLGEMMLowpMatrixMultiplyReshapedOnlyRHSKernel (const CLGEMMLowpMatrixMultiplyReshapedOnlyRHSKernel &)=delete
 Prevent instances of this class from being copied (As this class contains pointers) More...
 
CLGEMMLowpMatrixMultiplyReshapedOnlyRHSKerneloperator= (const CLGEMMLowpMatrixMultiplyReshapedOnlyRHSKernel &)=delete
 Prevent instances of this class from being copied (As this class contains pointers) More...
 
 CLGEMMLowpMatrixMultiplyReshapedOnlyRHSKernel (CLGEMMLowpMatrixMultiplyReshapedOnlyRHSKernel &&)=default
 Allow instances of this class to be moved. More...
 
CLGEMMLowpMatrixMultiplyReshapedOnlyRHSKerneloperator= (CLGEMMLowpMatrixMultiplyReshapedOnlyRHSKernel &&)=default
 Allow instances of this class to be moved. More...
 
void configure (const ICLTensor *input0, const ICLTensor *input1, ICLTensor *output, const GEMMLHSMatrixInfo &lhs_info, const GEMMRHSMatrixInfo &rhs_info, const GEMMReshapeInfo &gemm_info)
 Initialise the kernel's input and output. More...
 
void run (const Window &window, cl::CommandQueue &queue) override
 Enqueue the OpenCL kernel to process the given window on the passed OpenCL command queue. More...
 
- Public Member Functions inherited from ICLKernel
 ICLKernel ()
 Constructor. More...
 
cl::Kernel & kernel ()
 Returns a reference to the OpenCL kernel of this object. 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...
 
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...
 
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...
 
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...
 
template<unsigned int dimension_size>
void add_tensor_argument (unsigned &idx, const ICLTensor *tensor, const Window &window)
 
- 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 *input0, const ITensorInfo *input1, const ITensorInfo *output, const GEMMLHSMatrixInfo &lhs_info, const GEMMRHSMatrixInfo &rhs_info, const GEMMReshapeInfo &gemm_info)
 Static function to check if given info will lead to a valid configuration of CLGEMMLowpMatrixMultiplyReshapedOnlyRHSKernel. More...
 
- Static Public Member Functions inherited from ICLKernel
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)
 Get the global work size given an execution window. More...
 

Detailed Description

OpenCL kernel to multiply matrices with QASYMM8 data type when only the input matrix RHS (input1) has been reshaped.

Note
The input matrix input1 must be reshaped through CLGEMMReshapeRHSMatrixKernel

Definition at line 37 of file CLGEMMLowpMatrixMultiplyReshapedOnlyRHSKernel.h.

Constructor & Destructor Documentation

◆ CLGEMMLowpMatrixMultiplyReshapedOnlyRHSKernel() [1/3]

Default Constructor.

Definition at line 167 of file CLGEMMLowpMatrixMultiplyReshapedOnlyRHSKernel.cpp.

168  : _input0(nullptr), _input1(nullptr), _output(nullptr), _slide_matrix_b(true), _reinterpret_input_as_3d(false), _reinterpret_output_as_3d(false), _use_dummy_work_items(false)
169 {
170 }

◆ CLGEMMLowpMatrixMultiplyReshapedOnlyRHSKernel() [2/3]

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

◆ CLGEMMLowpMatrixMultiplyReshapedOnlyRHSKernel() [3/3]

Allow instances of this class to be moved.

Member Function Documentation

◆ configure()

void configure ( const ICLTensor input0,
const ICLTensor input1,
ICLTensor output,
const GEMMLHSMatrixInfo lhs_info,
const GEMMRHSMatrixInfo rhs_info,
const GEMMReshapeInfo gemm_info 
)

Initialise the kernel's input and output.

Parameters
[in]input0Input tensor containing the LHS matrix. Data type supported: QASYMM8
[in]input1Input tensor containing the RHS reshaped matrix. Data type supported: same as input0
[out]outputOutput tensor to store the result of matrix multiplication. Data type supported: S32
[in]lhs_infoLHS matrix information used to retrieve the number of rows to be processed by each thread lhs_info.m0: 2,3,4,5,6,7,8 lhs_info.k0: 2,3,4,8,16
[in]rhs_infoRHS matrix information used for reshaping the input1 tensor. Only the following values are supported: rhs_info.n0: 2,3,4,8,16 rhs_info.k0: 2,3,4,8,16 rhs_info.transpose: true
[in]gemm_infoGEMM information used to retrieve the original dimensions of the input matrices

Definition at line 172 of file CLGEMMLowpMatrixMultiplyReshapedOnlyRHSKernel.cpp.

174 {
175  ARM_COMPUTE_ERROR_ON_NULLPTR(input0, input1, output);
176 
177  ARM_COMPUTE_ERROR_THROW_ON(validate_arguments(input0->info(), input1->info(), output->info(), lhs_info, rhs_info, gemm_info));
178 
179  _input0 = input0;
180  _input1 = input1;
181  _output = output;
182  _reinterpret_input_as_3d = gemm_info.reinterpret_input_as_3d();
183  _reinterpret_output_as_3d = (gemm_info.depth_output_gemm3d() != 0);
184  _use_dummy_work_items = preferred_dummy_work_items_support(CLKernelLibrary::get().get_device());
185 
186  // In case both input and output have to be reinterpreted as 3D tensors,
187  // force reinterpret_input_as_3d and reinterpret_output_as_3d to be false.
188  if(_reinterpret_input_as_3d == _reinterpret_output_as_3d)
189  {
190  _reinterpret_input_as_3d = false;
191  _reinterpret_output_as_3d = false;
192  }
193 
194  // Check if we need to slide the matrix B
195  const unsigned int num_dimensions_input0 = _input0->info()->num_dimensions();
196  _slide_matrix_b = (_input1->info()->num_dimensions() >= num_dimensions_input0);
197 
198  ElementsProcessed num_elements_processed{};
199 
200  // Configure kernel window
201  auto win_config = validate_and_configure_window(input0->info(), input1->info(), output->info(), lhs_info, rhs_info, gemm_info, num_elements_processed);
202  ARM_COMPUTE_ERROR_THROW_ON(win_config.first);
203  ICLKernel::configure_internal(win_config.second);
204 
205  // Create build options
206  CLBuildOptions build_opts;
207  build_opts.add_option_if(_reinterpret_input_as_3d, "-DREINTERPRET_INPUT_AS_3D");
208  build_opts.add_option_if(_reinterpret_output_as_3d, "-DREINTERPRET_OUTPUT_AS_3D");
209  build_opts.add_option_if(_reinterpret_input_as_3d || _reinterpret_output_as_3d, "-DHEIGHT_GEMM3D=" + support::cpp11::to_string(output->info()->dimension(1)));
210  build_opts.add_option_if(_reinterpret_input_as_3d || _reinterpret_output_as_3d, "-DDEPTH_GEMM3D=" + support::cpp11::to_string(output->info()->dimension(2)));
211  build_opts.add_option_if(!_slide_matrix_b, "-DMATRIX_B_DEPTH=" + support::cpp11::to_string(input1->info()->dimension(2)));
212  build_opts.add_option_if(rhs_info.interleave, "-DRHS_INTERLEAVE");
213  build_opts.add_option_if(_use_dummy_work_items, "-DDUMMY_WORK_ITEMS");
214  build_opts.add_option("-DM=" + support::cpp11::to_string(input0->info()->dimension(1)));
215  build_opts.add_option("-DN=" + support::cpp11::to_string(gemm_info.n()));
216  build_opts.add_option("-DK=" + support::cpp11::to_string(gemm_info.k()));
217  build_opts.add_option("-DM0=" + support::cpp11::to_string(lhs_info.m0));
218  build_opts.add_option("-DN0=" + support::cpp11::to_string(rhs_info.n0));
219  build_opts.add_option("-DK0=" + support::cpp11::to_string(rhs_info.k0));
220  build_opts.add_option("-DH0=" + support::cpp11::to_string(rhs_info.h0));
221 
222  std::string kernel_name("gemmlowp_mm_reshaped_only_rhs_");
223  kernel_name += rhs_info.transpose ? "t" : "nt";
224 
225  // Create kernel
226  _kernel = static_cast<cl::Kernel>(CLKernelLibrary::get().create_kernel(kernel_name, build_opts.options()));
227 
228  // Set config_id for enabling LWS tuning
229  _config_id = kernel_name;
230  _config_id += "_";
231  _config_id += dot8_supported(CLKernelLibrary::get().get_device()) ? "_dot8" : "";
232  _config_id += "_";
233  _config_id += (_reinterpret_input_as_3d ? "3di_" : "");
234  _config_id += (_reinterpret_output_as_3d ? "3do_" : "");
235  _config_id += support::cpp11::to_string(output->info()->dimension(1));
236  _config_id += "_";
237  _config_id += support::cpp11::to_string(output->info()->dimension(0));
238  _config_id += "_";
239  _config_id += support::cpp11::to_string(gemm_info.k());
240  _config_id += "_";
241  _config_id += support::cpp11::to_string(output->info()->dimension(2));
242  _config_id += "_";
243  _config_id += support::cpp11::to_string(lhs_info.m0);
244  _config_id += "_";
245  _config_id += support::cpp11::to_string(rhs_info.n0);
246  _config_id += "_";
247  _config_id += support::cpp11::to_string(rhs_info.k0);
248  _config_id += "_";
249  _config_id += support::cpp11::to_string(rhs_info.h0);
250  _config_id += "_";
251  _config_id += support::cpp11::to_string(rhs_info.interleave);
252 }
virtual size_t num_dimensions() const =0
The number of dimensions of the tensor (rank)
bool dot8_supported(const cl::Device &device)
Helper function to check whether the cl_arm_integer_dot_product_int8 extension is supported.
Definition: CLHelpers.cpp:204
bool preferred_dummy_work_items_support(const cl::Device &device)
Helper function to check if "dummy work-items" are preferred to have a power of two NDRange In case d...
Definition: CLHelpers.cpp:325
std::string to_string(T &&value)
Convert integer and float values to string.
static CLKernelLibrary & get()
Access the KernelLibrary singleton.
#define ARM_COMPUTE_ERROR_THROW_ON(status)
Definition: Error.h:455
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_NULLPTR(...)
Definition: Validate.h:161

References CLBuildOptions::add_option(), CLBuildOptions::add_option_if(), ARM_COMPUTE_ERROR_ON_NULLPTR, ARM_COMPUTE_ERROR_THROW_ON, arm_compute::create_kernel(), GEMMReshapeInfo::depth_output_gemm3d(), ITensorInfo::dimension(), arm_compute::dot8_supported(), CLKernelLibrary::get(), ITensor::info(), GEMMLHSMatrixInfo::m0, ITensorInfo::num_dimensions(), CLBuildOptions::options(), arm_compute::preferred_dummy_work_items_support(), GEMMReshapeInfo::reinterpret_input_as_3d(), and arm_compute::support::cpp11::to_string().

Referenced by CLGEMMLowpMatrixMultiplyCore::configure().

◆ operator=() [1/2]

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

◆ operator=() [2/2]

Allow instances of this class to be moved.

◆ run()

void run ( const Window window,
cl::CommandQueue &  queue 
)
overridevirtual

Enqueue the OpenCL kernel to process the given window on the passed OpenCL command queue.

Note
The queue is not flushed by this method, and therefore the kernel will not have been executed by the time this method returns.
Parameters
[in]windowRegion on which to execute the kernel. (Must be a valid region of the window returned by window()).
[in,out]queueCommand queue on which to enqueue the kernel.

Implements ICLKernel.

Definition at line 271 of file CLGEMMLowpMatrixMultiplyReshapedOnlyRHSKernel.cpp.

272 {
275 
276  if(_input1->info()->num_dimensions() < 3)
277  {
278  // The stride_z for matrix B must be zero if we do not slice
279  ARM_COMPUTE_ERROR_ON(_input1->info()->strides_in_bytes()[3] != 0);
280  }
281 
283  Window slice_matrix_b = slice;
284 
285  slice_matrix_b.set(Window::DimX, Window::Dimension(0, 1, 1));
286  slice_matrix_b.set(Window::DimY, Window::Dimension(0, 1, 1));
287 
288  if(_reinterpret_input_as_3d)
289  {
290  // Pass bottom paddings to the kernel if the input has to be reinterpreted as 3D tensor
291  const unsigned int idx0 = 3 * num_arguments_per_2D_tensor() + 3;
292  const unsigned int total_cross_plane_pad = _input0->info()->padding().top + _input0->info()->padding().bottom;
293  _kernel.setArg<cl_uint>(idx0, static_cast<unsigned int>(total_cross_plane_pad));
294  }
295 
296  if(_reinterpret_output_as_3d)
297  {
298  // Pass bottom paddings to the kernel if the output has to be reinterpreted as 3D tensor
299  const unsigned int idx0 = 3 * num_arguments_per_2D_tensor() + 3 + (_reinterpret_input_as_3d ? 1 : 0);
300  const unsigned int total_cross_plane_pad = _output->info()->padding().top + _output->info()->padding().bottom;
301  _kernel.setArg<cl_uint>(idx0, static_cast<unsigned int>(total_cross_plane_pad));
302  }
303 
304  do
305  {
306  Window slice_b = slice;
307  // Don't slice matrix B along the z dimension if matrix B has just 2 dimensions and matrix A more than 2
308  // This scenario can happen when the matrix multiplication is used to perform a convolution operation
309  if(!_slide_matrix_b)
310  {
311  slice_b = slice_matrix_b;
312  }
313 
314  unsigned int idx = 0;
315  add_2D_tensor_argument(idx, _input0, slice);
316  add_2D_tensor_argument(idx, _input1, slice_b);
317  add_2D_tensor_argument(idx, _output, slice);
318  _kernel.setArg<cl_uint>(idx++, static_cast<unsigned int>(_input0->info()->strides_in_bytes()[2]));
319  _kernel.setArg<cl_uint>(idx++, static_cast<unsigned int>(_input1->info()->strides_in_bytes()[2]));
320  _kernel.setArg<cl_uint>(idx++, static_cast<unsigned int>(_output->info()->strides_in_bytes()[2]));
321  enqueue(queue, *this, slice, lws_hint(), _use_dummy_work_items);
322  }
324 }
unsigned int top
top of the border
Definition: Types.h:348
virtual size_t num_dimensions() const =0
The number of dimensions of the tensor (rank)
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:39
cl::NDRange lws_hint() const
Return the Local-Workgroup-Size hint.
Definition: ICLKernel.h:247
#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
unsigned int bottom
bottom of the border
Definition: Types.h:350
static constexpr size_t DimX
Alias for dimension 0 also known as X dimension.
Definition: Window.h:43
virtual ITensorInfo * info() const =0
Interface to be implemented by the child class to return the tensor's metadata.
virtual PaddingSize padding() const =0
Padding of tensor.
static constexpr unsigned int num_arguments_per_2D_tensor()
Returns the number of arguments enqueued per 2D tensor object.
Definition: ICLKernel.h:192
bool slide_window_slice_3D(Window &slice) const
Slide the passed 3D window slice.
Definition: Window.h:333
static constexpr size_t DimY
Alias for dimension 1 also known as Y dimension.
Definition: Window.h:45
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.
Definition: ICLKernel.h:134
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:289
#define ARM_COMPUTE_ERROR_ON_INVALID_SUBWINDOW(f, s)
Definition: Validate.h:205
#define ARM_COMPUTE_ERROR_ON_UNCONFIGURED_KERNEL(k)
Definition: Validate.h:941
SimpleTensor< T > slice(const SimpleTensor< T > &src, Coordinates starts, Coordinates ends)

References ICLKernel::add_2D_tensor_argument(), ARM_COMPUTE_ERROR_ON, ARM_COMPUTE_ERROR_ON_INVALID_SUBWINDOW, ARM_COMPUTE_ERROR_ON_UNCONFIGURED_KERNEL, BorderSize::bottom, Window::DimX, Window::DimY, arm_compute::enqueue(), Window::first_slice_window_3D(), ITensor::info(), ICLKernel::lws_hint(), ICLKernel::num_arguments_per_2D_tensor(), ITensorInfo::num_dimensions(), ITensorInfo::padding(), Window::set(), arm_compute::test::validation::reference::slice(), Window::slide_window_slice_3D(), ITensorInfo::strides_in_bytes(), BorderSize::top, and IKernel::window().

◆ validate()

Status validate ( const ITensorInfo input0,
const ITensorInfo input1,
const ITensorInfo output,
const GEMMLHSMatrixInfo lhs_info,
const GEMMRHSMatrixInfo rhs_info,
const GEMMReshapeInfo gemm_info 
)
static

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

Parameters
[in]input0Input tensor info for the LHS matrix. Data type supported: QASYMM8
[in]input1Input tensor info for the RHS reshaped matrix. Data type supported: same as input0
[in]outputOutput tensor info. Data type supported: S32
[in]lhs_infoLHS matrix information used to retrieve the number of rows to be processed by each thread lhs_info.m0: 2,3,4,5,6,7,8 lhs_info.k0: 2,3,4,8,16
[in]rhs_infoRHS matrix information used for reshaping the input1 tensor. Only the following values are supported: rhs_info.n0: 2,3,4,8,16 rhs_info.k0: same as lhs_info.k0 rhs_info.transpose: true
[in]gemm_infoGEMM information used to retrieve the original dimensions of the input matrices
Returns
a status

Definition at line 254 of file CLGEMMLowpMatrixMultiplyReshapedOnlyRHSKernel.cpp.

256 {
257  ElementsProcessed num_elements_processed{};
258  ARM_COMPUTE_RETURN_ON_ERROR(validate_arguments(input0, input1, output, lhs_info, rhs_info, gemm_info));
259  ARM_COMPUTE_RETURN_ON_ERROR(validate_and_configure_window(input0->clone().get(),
260  input1->clone().get(),
261  output->clone().get(),
262  lhs_info,
263  rhs_info,
264  gemm_info,
265  num_elements_processed)
266  .first);
267 
268  return Status{};
269 }
#define ARM_COMPUTE_RETURN_ON_ERROR(status)
Checks if a status contains an error and returns it.
Definition: Error.h:204

References ARM_COMPUTE_RETURN_ON_ERROR, and ICloneable< T >::clone().

Referenced by CLGEMMLowpMatrixMultiplyCore::validate().


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