Compute Library
 21.02
CLDepthwiseConvolutionLayer3x3NHWCKernel.cpp
Go to the documentation of this file.
1 /*
2  * Copyright (c) 2018-2021 Arm Limited.
3  *
4  * SPDX-License-Identifier: MIT
5  *
6  * Permission is hereby granted, free of charge, to any person obtaining a copy
7  * of this software and associated documentation files (the "Software"), to
8  * deal in the Software without restriction, including without limitation the
9  * rights to use, copy, modify, merge, publish, distribute, sublicense, and/or
10  * sell copies of the Software, and to permit persons to whom the Software is
11  * furnished to do so, subject to the following conditions:
12  *
13  * The above copyright notice and this permission notice shall be included in all
14  * copies or substantial portions of the Software.
15  *
16  * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
17  * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
18  * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE
19  * AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
20  * LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM,
21  * OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE
22  * SOFTWARE.
23  */
25 
31 #include "arm_compute/core/Utils.h"
35 #include "src/core/CL/CLValidate.h"
36 #include "src/core/CL/ICLKernel.h"
39 #include "support/StringSupport.h"
40 
41 namespace arm_compute
42 {
43 namespace
44 {
45 Status validate_arguments(const ITensorInfo *input, const ITensorInfo *weights, const ITensorInfo *biases, const ITensorInfo *output,
46  const PadStrideInfo &conv_info, unsigned int depth_multiplier, const ActivationLayerInfo &act_info, const Size2D &dilation,
47  const ITensorInfo *output_multipliers, const ITensorInfo *output_shifts)
48 {
51  ARM_COMPUTE_RETURN_ERROR_ON_MSG((act_info.enabled()) && (input->data_type() == DataType::QASYMM8 || input->data_type() == DataType::QASYMM8_SIGNED)
53  && (act_info.activation() != ActivationLayerInfo::ActivationFunction::BOUNDED_RELU)
54  && (act_info.activation() != ActivationLayerInfo::ActivationFunction::RELU)
55  && (act_info.activation() != ActivationLayerInfo::ActivationFunction::LOGISTIC),
56  "For QASYMM8 only logistic, relu, lower bounded relu and lower-upper bounded relu are supported");
57  ARM_COMPUTE_RETURN_ERROR_ON(depth_multiplier > 1); // COMPMID-1071 Add depth multiplier support for NHWC
58 
59  ARM_COMPUTE_RETURN_ERROR_ON(conv_info.stride().first < 1);
60  ARM_COMPUTE_RETURN_ERROR_ON(std::max(conv_info.pad_top(), conv_info.pad_bottom()) > 4);
61 
62  ARM_COMPUTE_RETURN_ERROR_ON((dilation.x() < 1) || (dilation.y() < 1));
63 
64  const bool is_qasymm = is_data_type_quantized_asymmetric(input->data_type());
65  const size_t weights_width = 3;
66  const size_t weights_height = 3;
67 
69  *input, TensorInfo(TensorShape(weights_width, weights_height), 1, weights->data_type()).set_data_layout(DataLayout::NCHW), conv_info, depth_multiplier, dilation);
70  if(is_qasymm)
71  {
72  DepthwiseConvolutionReshapeInfo info;
73  info.c0 = 4;
74  ARM_COMPUTE_RETURN_ERROR_ON((weights->dimension(0) / info.c0) != weights_width * weights_height);
75 
76  ARM_COMPUTE_RETURN_ERROR_ON_NULLPTR(output_multipliers, output_shifts);
79  ARM_COMPUTE_RETURN_ERROR_ON(output_multipliers->num_dimensions() > 1);
80  ARM_COMPUTE_RETURN_ERROR_ON(output_shifts->num_dimensions() > 1);
81 
82  if(is_data_type_quantized_per_channel(weights->data_type()))
83  {
84  ARM_COMPUTE_RETURN_ERROR_ON(output_shape[0] != output_multipliers->dimension(0));
85  ARM_COMPUTE_RETURN_ERROR_ON(output_shape[0] != output_shifts->dimension(0));
86  }
87  else
88  {
90  ARM_COMPUTE_RETURN_ERROR_ON(1 != output_multipliers->dimension(0));
91  ARM_COMPUTE_RETURN_ERROR_ON(1 != output_shifts->dimension(0));
92  }
93  }
94  else
95  {
97  ARM_COMPUTE_RETURN_ERROR_ON((weights->dimension(1) != weights_width) || (weights->dimension(2) != weights_height));
98  }
99 
100  if(biases != nullptr)
101  {
102  ARM_COMPUTE_RETURN_ERROR_ON(biases->dimension(0) != output_shape[0]);
103  if(is_qasymm)
104  {
106  }
107  else
108  {
110  }
111 
112  ARM_COMPUTE_RETURN_ERROR_ON(biases->num_dimensions() > 1);
113  }
114 
115  if(output->total_size() != 0)
116  {
118  }
119 
120  return Status{};
121 }
122 
123 std::pair<Status, Window> validate_and_configure_window(ITensorInfo *input, ITensorInfo *weights, ITensorInfo *bias, ITensorInfo *output,
124  const PadStrideInfo &conv_info, unsigned int depth_multiplier, const Size2D &dilation,
125  ITensorInfo *output_multipliers, ITensorInfo *output_shifts)
126 {
127  ARM_COMPUTE_UNUSED(weights);
128  ARM_COMPUTE_UNUSED(depth_multiplier);
129 
130  const bool is_stride_1_dilation_1 = ((conv_info.stride().first == conv_info.stride().second) && (conv_info.stride().first == 1) && dilation.x() == 1 && dilation.y() == 1);
131  unsigned int num_rows_processed_per_iteration = is_stride_1_dilation_1 ? 2 : 1;
132 
133  Window win{};
134  Status err{};
135 
136  if(is_data_type_quantized_asymmetric(input->data_type()))
137  {
138  const unsigned int num_elems_accessed_per_iteration = 4;
139  const unsigned int num_rows_read_per_iteration = num_rows_processed_per_iteration + 2;
140  const unsigned int num_rows_written_per_iteration = std::ceil(num_rows_processed_per_iteration / static_cast<float>(conv_info.stride().first));
141 
142  BorderSize border_size;
143  border_size = BorderSize(conv_info.pad_left(), 0, std::max(std::max(conv_info.pad_right(), conv_info.pad_bottom()), conv_info.pad_top()), 0);
144 
145  // Configure kernel window
146  win = calculate_max_window(*output, Steps(num_elems_accessed_per_iteration, num_rows_written_per_iteration));
147 
148  AccessWindowStatic input_access(input, 0, -border_size.top, ceil_to_multiple(input->dimension(0), num_elems_accessed_per_iteration),
149  ceil_to_multiple(input->dimension(1) + border_size.bottom, num_rows_read_per_iteration));
150  AccessWindowRectangle output_access(output, 0, 0, num_elems_accessed_per_iteration, num_rows_written_per_iteration);
151 
152  bool window_changed = false;
153 
154  if((output_multipliers != nullptr) && (output_shifts != nullptr))
155  {
156  AccessWindowHorizontal output_multipliers_access(output_multipliers, 0, num_elems_accessed_per_iteration);
157  AccessWindowHorizontal output_shifts_access(output_shifts, 0, num_elems_accessed_per_iteration);
158  window_changed = window_changed || update_window_and_padding(win, input_access, output_access, output_multipliers_access, output_shifts_access);
159  }
160  else
161  {
162  Status err = ARM_COMPUTE_CREATE_ERROR(ErrorCode::RUNTIME_ERROR, "output_multipliers and output_shifts must be non-nullptr for quantized input");
163  return std::make_pair(err, win);
164  }
165 
166  if(bias != nullptr)
167  {
168  AccessWindowHorizontal bias_access(bias, 0, num_elems_accessed_per_iteration);
169  window_changed = window_changed || update_window_and_padding(win, bias_access);
170  }
171  output_access.set_valid_region(win, ValidRegion(Coordinates(), output->tensor_shape()));
172 
173  err = (window_changed) ? ARM_COMPUTE_CREATE_ERROR(ErrorCode::RUNTIME_ERROR, "Insufficient Padding!") : Status{};
174  }
175  else
176  {
177  unsigned int num_elems_accessed_per_iteration = adjust_vec_size(4 / input->element_size(), input->dimension(0));
178  win = calculate_max_window(*output, Steps(num_elems_accessed_per_iteration, num_rows_processed_per_iteration));
179  }
180 
181  return std::make_pair(err, win);
182 }
183 } // namespace
184 
186  : _num_planes_processed_per_iteration(1)
187 {
188 }
189 
191 {
192  return _border_size;
193 }
194 
195 void CLDepthwiseConvolutionLayer3x3NHWCKernel::configure(const ICLTensor *input, const ICLTensor *weights, const ICLTensor *biases, ICLTensor *output,
196  const PadStrideInfo &conv_info, unsigned int depth_multiplier, ActivationLayerInfo act_info, const Size2D &dilation,
197  const ICLTensor *output_multipliers, const ICLTensor *output_shifts)
198 {
199  configure(CLKernelLibrary::get().get_compile_context(), input, weights, biases, output, conv_info, depth_multiplier, act_info, dilation, output_multipliers, output_shifts);
200 }
201 
202 void CLDepthwiseConvolutionLayer3x3NHWCKernel::configure(const CLCompileContext &compile_context, const ICLTensor *input, const ICLTensor *weights, const ICLTensor *biases, ICLTensor *output,
203  const PadStrideInfo &conv_info, unsigned int depth_multiplier, ActivationLayerInfo act_info, const Size2D &dilation,
204  const ICLTensor *output_multipliers, const ICLTensor *output_shifts)
205 {
206  ARM_COMPUTE_ERROR_ON_NULLPTR(input, weights, output);
207  ARM_COMPUTE_ERROR_THROW_ON(validate_arguments(input->info(), weights->info(), (biases != nullptr) ? biases->info() : nullptr, output->info(),
208  conv_info, depth_multiplier, act_info, dilation,
209  (output_multipliers != nullptr) ? output_multipliers->info() : nullptr,
210  (output_shifts != nullptr) ? output_shifts->info() : nullptr));
211 
212  auto padding_info = get_padding_info({ input, weights, biases, output });
213 
214  auto win_config = validate_and_configure_window(input->info(), weights->info(), biases != nullptr ? biases->info() : nullptr, output->info(),
215  conv_info, depth_multiplier, dilation,
216  (output_multipliers != nullptr) ? output_multipliers->info() : nullptr,
217  (output_shifts != nullptr) ? output_shifts->info() : nullptr);
218 
219  const bool is_stride_1 = ((conv_info.stride().first == conv_info.stride().second) && (conv_info.stride().first == 1));
220  const bool is_stride_1_dilation_1 = (is_stride_1 && dilation.x() == 1 && dilation.y() == 1);
221  const bool is_quantized_per_channel = is_data_type_quantized_per_channel(weights->info()->data_type());
222  const bool is_dot8_supported = dot8_supported(CLKernelLibrary::get().get_device()) && !is_quantized_per_channel;
223 
224  _input = input;
225  _output = output;
226  _weights = weights;
227  _biases = biases;
228  _conv_stride_y = conv_info.stride().second;
229  _num_planes_processed_per_iteration = is_stride_1_dilation_1 ? 2 : 1;
230  _output_multipliers = output_multipliers;
231  _output_shifts = output_shifts;
232  _is_quantized = is_data_type_quantized_asymmetric(input->info()->data_type());
233 
234  if(_is_quantized)
235  {
236  _border_size = BorderSize(input->info()->padding());
237 
238  // If QASYMM8 and the 8 bit dot product is available, force _num_planes_processed_per_iteration to 1
239  if(is_dot8_supported)
240  {
241  _num_planes_processed_per_iteration = 1;
242  }
243  }
244 
245  unsigned int num_elems_accessed_per_iteration = _is_quantized ? 4 : adjust_vec_size(4 / input->info()->element_size(), input->info()->dimension(0));
246  unsigned int num_rows_processed_per_iteration = is_stride_1_dilation_1 ? 2 : 1;
247 
248  CLBuildOptions build_opts;
249  build_opts.add_option("-DDATA_TYPE=" + get_cl_type_from_data_type(_input->info()->data_type()));
250  build_opts.add_option("-DACTIVATION_TYPE=" + lower_string(string_from_activation_func(act_info.activation())));
251  build_opts.add_option("-DVEC_SIZE=" + support::cpp11::to_string(num_elems_accessed_per_iteration));
252  build_opts.add_option("-DSRC_DIM_1=" + support::cpp11::to_string(_input->info()->dimension(1)));
253  build_opts.add_option("-DSRC_DIM_2=" + support::cpp11::to_string(_input->info()->dimension(2)));
254  build_opts.add_option("-DCONV_PAD_TOP=" + support::cpp11::to_string(conv_info.pad_top()));
255  build_opts.add_option("-DCONV_PAD_LEFT=" + support::cpp11::to_string(conv_info.pad_left()));
256  build_opts.add_option("-DPARTIAL_STORE_N0=" + support::cpp11::to_string(input->info()->dimension(0) % num_elems_accessed_per_iteration));
257  build_opts.add_option_if(_biases != nullptr, "-DHAS_BIAS");
258  build_opts.add_option_if(_input->info()->tensor_shape().total_size_upper(3) > 1,
259  "-DDST_DEPTH=" + support::cpp11::to_string(static_cast<int>(std::ceil(_output->info()->dimension(2) / static_cast<float>(_num_planes_processed_per_iteration)))));
260 
261  if(_is_quantized)
262  {
263  const UniformQuantizationInfo iq_info = _input->info()->quantization_info().uniform();
264  const UniformQuantizationInfo wq_info = _weights->info()->quantization_info().uniform();
265  const UniformQuantizationInfo oq_info = _output->info()->quantization_info().uniform();
266 
267  build_opts.add_option("-DSRC_DIM_1=" + support::cpp11::to_string(_input->info()->dimension(1)));
268  build_opts.add_option("-DINPUT_OFFSET=" + support::cpp11::to_string(-iq_info.offset));
269  build_opts.add_option("-DWEIGHTS_OFFSET=" + support::cpp11::to_string(-wq_info.offset));
270  build_opts.add_option("-DOUTPUT_OFFSET=" + support::cpp11::to_string(oq_info.offset));
271  build_opts.add_option("-DK_OFFSET=" + support::cpp11::to_string(9 * iq_info.offset * wq_info.offset));
272  build_opts.add_option_if(is_quantized_per_channel, "-DPER_CHANNEL_QUANTIZATION");
273  build_opts.add_option_if(is_dot8_supported, "-DIS_DOT8");
274 
275  // Compute non-per-channel multiplier and shift anyway to make OpenCL kernel simpler
276  float multiplier = iq_info.scale * wq_info.scale / oq_info.scale;
277  int output_multiplier = 0;
278  int output_shift = 0;
279  quantization::calculate_quantized_multiplier(multiplier, &output_multiplier, &output_shift);
280  build_opts.add_option("-DOUTPUT_MULTIPLIER=" + support::cpp11::to_string(output_multiplier));
281  build_opts.add_option("-DOUTPUT_SHIFT=" + support::cpp11::to_string(output_shift));
282 
283  if(act_info.enabled())
284  {
285  int a_val{};
286  int b_val{};
287  std::tie(b_val, a_val) = get_quantized_activation_min_max(act_info, input->info()->data_type(), oq_info);
288 
289  const int o1 = oq_info.offset;
290 
291  build_opts.add_option("-DA_VAL=" + support::cpp11::to_string(a_val));
292  build_opts.add_option("-DB_VAL=" + support::cpp11::to_string(b_val));
293  build_opts.add_option("-DCONST_0=" + support::cpp11::to_string(o1));
294 
295  const float s1 = iq_info.scale;
296  build_opts.add_option("-DS1_VAL=" + float_to_string_with_full_precision(s1));
297  build_opts.add_option("-DO1_VAL=" + support::cpp11::to_string(o1));
298  }
299 
300  build_opts.add_option("-DWEIGHTS_TYPE=" + get_cl_type_from_data_type(weights->info()->data_type()));
301  build_opts.add_option("-DWEIGHTS_PROMOTED_TYPE=" + get_cl_promoted_type_from_data_type(weights->info()->data_type()));
302  }
303  else
304  {
305  build_opts.add_option_if(act_info.enabled(), "-DA_VAL=" + float_to_string_with_full_precision(act_info.a()));
306  build_opts.add_option_if(act_info.enabled(), "-DB_VAL=" + float_to_string_with_full_precision(act_info.b()));
307  }
308 
309  if(is_stride_1_dilation_1)
310  {
311  build_opts.add_option("-DNUM_ROWS_PROCESSED=" + support::cpp11::to_string(num_rows_processed_per_iteration));
312  build_opts.add_option("-DNUM_PLANES_PROCESSED=" + support::cpp11::to_string(_num_planes_processed_per_iteration));
313  build_opts.add_option("-DDST_DIM_1=" + support::cpp11::to_string(_output->info()->dimension(1)));
314  build_opts.add_option("-DDST_DIM_2=" + support::cpp11::to_string(_output->info()->dimension(2)));
315  build_opts.add_option("-DPARTIAL_STORE_M0=" + support::cpp11::to_string((input->info()->dimension(1) + conv_info.pad_left() + conv_info.pad_right()) % num_rows_processed_per_iteration));
316  }
317  else
318  {
319  build_opts.add_option("-DCONV_STRIDE_X=" + support::cpp11::to_string(conv_info.stride().first));
320  build_opts.add_option("-DCONV_STRIDE_Y=" + support::cpp11::to_string(_conv_stride_y));
321  build_opts.add_option("-DDILATION_X=" + support::cpp11::to_string(dilation.x()));
322  build_opts.add_option("-DDILATION_Y=" + support::cpp11::to_string(dilation.y()));
323  }
324 
325  std::string kernel_name;
326  // Create kernel
327  if(_is_quantized)
328  {
329  kernel_name = std::string("dwc_3x3_reshaped_quantized8");
330  kernel_name += (is_dot8_supported && is_stride_1_dilation_1 ? "_dot8" : "");
331  kernel_name += (is_stride_1_dilation_1 ? "_stride1" : "");
332  kernel_name += "_nhwc";
333  }
334  else
335  {
336  kernel_name = std::string("depthwise_convolution_3x3_nhwc");
337  kernel_name += (is_stride_1_dilation_1 ? "_stride1" : "");
338  }
339 
340  ICLKernel::configure_internal(win_config.second);
341  _kernel = create_kernel(compile_context, kernel_name, build_opts.options());
342 
343  ARM_COMPUTE_ERROR_ON(!_is_quantized && has_padding_changed(padding_info));
344 
345  // Set config_id for enabling LWS tuning
346  _config_id = kernel_name;
347  _config_id += "_";
348  _config_id += support::cpp11::to_string(input->info()->dimension(0));
349  _config_id += "_";
350  _config_id += support::cpp11::to_string(input->info()->dimension(1));
351  _config_id += "_";
352  _config_id += support::cpp11::to_string(input->info()->dimension(2));
353  _config_id += "_";
354  _config_id += support::cpp11::to_string(output->info()->dimension(0));
355  _config_id += "_";
356  _config_id += support::cpp11::to_string(output->info()->dimension(1));
357  _config_id += "_";
358  _config_id += string_from_data_type(input->info()->data_type());
359 }
360 
362  const PadStrideInfo &conv_info, unsigned int depth_multiplier, ActivationLayerInfo act_info, const Size2D &dilation,
363  const ITensorInfo *output_multipliers, const ITensorInfo *output_shifts)
364 {
365  ARM_COMPUTE_RETURN_ON_ERROR(validate_arguments(input, weights, biases, output, conv_info, depth_multiplier, act_info, dilation, output_multipliers, output_shifts));
366  ARM_COMPUTE_RETURN_ON_ERROR(validate_and_configure_window(input->clone().get(), weights->clone().get(),
367  biases != nullptr ? biases->clone().get() : nullptr,
368  output->clone().get(), conv_info, depth_multiplier, dilation,
369  (output_multipliers != nullptr) ? output_multipliers->clone().get() : nullptr,
370  (output_shifts != nullptr) ? output_shifts->clone().get() : nullptr)
371  .first);
372  return Status{};
373 }
374 
375 void CLDepthwiseConvolutionLayer3x3NHWCKernel::run(const Window &window, cl::CommandQueue &queue)
376 {
379 
380  const size_t total_batches = _input->info()->tensor_shape().total_size_upper(3);
381 
383  win.set(Window::DimZ, Window::Dimension(0, std::ceil(_output->info()->dimension(2) / static_cast<float>(_num_planes_processed_per_iteration)) * total_batches, 1));
384 
385  unsigned int idx = 2 * num_arguments_per_4D_tensor() + (_is_quantized ? num_arguments_per_2D_tensor() : num_arguments_per_3D_tensor());
386 
387  if(_is_quantized)
388  {
389  Window slice;
390  slice.use_tensor_dimensions(_output_multipliers->info()->tensor_shape());
391  slice.set_dimension_step(Window::DimX, window.x().step());
392  add_1D_tensor_argument(idx, _output_multipliers, slice);
393  add_1D_tensor_argument(idx, _output_shifts, slice);
394  }
395 
396  if(_biases != nullptr)
397  {
398  Window win_biases;
399  win_biases.use_tensor_dimensions(_biases->info()->tensor_shape());
400  win_biases.set_dimension_step(Window::DimX, window.x().step());
401  add_1D_tensor_argument(idx, _biases, win_biases);
402  }
403 
404  if(_is_quantized)
405  {
406  // Calculate the max_offset.
407  // max_offset is the offset for the last NOT valid value in the Z dimension (spatial dimension Y for NHWC)
408  // |******************|
409  // | pad_top |
410  // |******************|
411  // | |
412  // | plane0 |
413  // | batch0 |
414  // |__________________|
415  // |******************| Batch 0
416  // | pad_bottom |
417  // | pad_top |
418  // |******************|
419  // | |
420  // | plane1 |
421  // | batch0 |
422  // |__________________|-----> max_offset
423  // |******************|
424  // | pad_bottom |
425  // | pad_top |
426  // |******************|
427  // | |
428  // | plane0 |
429  // | batch1 |
430  // |__________________|
431  // |******************| Batch 1
432  // | pad_bottom |
433  // | pad_top |
434  // |******************|
435  // | |
436  // | plane1 |
437  // | batch1 |
438  // |__________________|
439  // | pad_bottom |
440  // |******************|
441  const int max_offset = ((_input->info()->dimension(1) * _input->info()->dimension(2)) + (_input->info()->padding().bottom + _input->info()->padding().top) * (_input->info()->dimension(
442  2) - 1)) * _input->info()->strides_in_bytes().y();
443  _kernel.setArg(idx, max_offset);
444  }
445 
447  do
448  {
449  unsigned int idx = 0;
450  add_4D_tensor_argument(idx, _input, slice);
451  add_4D_tensor_argument(idx, _output, slice);
452  if(_is_quantized)
453  {
454  add_2D_tensor_argument(idx, _weights, slice);
455  }
456  else
457  {
458  add_3D_tensor_argument(idx, _weights, slice);
459  }
460  enqueue(queue, *this, slice, lws_hint());
461  }
462  while(win.slide_window_slice_4D(slice));
463 }
464 } // namespace arm_compute
void run(const Window &window, cl::CommandQueue &queue) override
Enqueue the OpenCL kernel to process the given window on the passed OpenCL command queue...
Window calculate_max_window(const ValidRegion &valid_region, const Steps &steps, bool skip_border, BorderSize border_size)
#define ARM_COMPUTE_RETURN_ERROR_ON_F16_UNSUPPORTED(tensor)
Definition: CLValidate.h:35
const Window & window() const
The maximum window the kernel can be executed on.
Definition: IKernel.cpp:28
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:239
void enqueue(IGCKernel &kernel, const Window &window, const gles::NDRange &lws=gles::NDRange(1U, 1U, 1U))
Add the kernel to the command queue with the given window.
Definition: IGCKernel.cpp:41
TensorShape compute_depthwise_convolution_shape(const ITensorInfo &input, const ITensorInfo &weights, PadStrideInfo conv_info, unsigned int depth_multiplier, const Size2D &dilation=Size2D(1U, 1U))
Calculate the depthwise convolution output shape of a tensor.
virtual size_t dimension(size_t index) const =0
Return the size of the requested dimension.
Container for 2D border size.
Definition: Types.h:273
const StringSet & options() const
Gets the current options list set.
constexpr int step() const
Return the step of the dimension.
Definition: Window.h:104
cl::NDRange lws_hint() const
Return the Local-Workgroup-Size hint.
Definition: ICLKernel.h:276
#define ARM_COMPUTE_RETURN_ON_ERROR(status)
Checks if a status contains an error and returns it.
Definition: Error.h:204
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
#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
const std::string & string_from_activation_func(ActivationLayerInfo::ActivationFunction act)
Translates a given activation function to a string.
Definition: Utils.cpp:163
static CLKernelLibrary & get()
Access the KernelLibrary singleton.
Store the tensor&#39;s metadata.
Definition: ITensorInfo.h:40
#define ARM_COMPUTE_ERROR_THROW_ON(status)
Definition: Error.h:455
Quantization info when assuming per layer quantization.
Describe one of the image&#39;s dimensions with a start, end and step.
Definition: Window.h:77
unsigned int pad_top() const
Get the top padding.
Definition: Types.h:806
Status calculate_quantized_multiplier(float multiplier, int32_t *quant_multiplier, int32_t *shift, bool ignore_epsilon=false)
Calculate quantized representation of multiplier.
Status class.
Definition: Error.h:52
std::string lower_string(const std::string &val)
Lower a given string.
Definition: Utils.cpp:350
#define ARM_COMPUTE_RETURN_ERROR_ON(cond)
If the condition is true, an error is returned.
Definition: Error.h:296
Activation Layer Information class.
Definition: Types.h:1550
#define ARM_COMPUTE_RETURN_ERROR_ON_MISMATCHING_DIMENSIONS(...)
Definition: Validate.h:288
void add_3D_tensor_argument(unsigned int &idx, const ICLTensor *tensor, const Window &window)
Add the passed 3D tensor&#39;s parameters to the object&#39;s kernel&#39;s arguments starting from the index idx...
Definition: ICLKernel.h:172
void use_tensor_dimensions(const TensorShape &shape, size_t first_dimension=Window::DimX)
Use the tensor&#39;s dimensions to fill the window dimensions.
Definition: Window.inl:276
Copyright (c) 2017-2021 Arm Limited.
1 channel, 1 F16 per channel
#define ARM_COMPUTE_RETURN_ERROR_ON_NULLPTR(...)
Definition: Validate.h:163
1 channel, 1 S32 per channel
void add_option(std::string option)
Adds option to the existing build option list.
static Status validate(const ITensorInfo *input, const ITensorInfo *weights, const ITensorInfo *biases, const ITensorInfo *output, const PadStrideInfo &conv_info, unsigned int depth_multiplier=1, ActivationLayerInfo act_info=ActivationLayerInfo(), const Size2D &dilation=Size2D(1U, 1U), const ITensorInfo *output_multipliers=nullptr, const ITensorInfo *output_shifts=nullptr)
Static function to check if given info will lead to a valid configuration of CLDepthwiseConvolutionLa...
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:403
const std::string & string_from_data_type(DataType dt)
Convert a data type identity into a string.
Definition: Utils.cpp:135
static constexpr size_t DimX
Alias for dimension 0 also known as X dimension.
Definition: Window.h:43
bool update_window_and_padding(Window &win, Ts &&... patterns)
Update window and padding size for each of the access patterns.
Definition: WindowHelpers.h:46
static constexpr unsigned int num_arguments_per_3D_tensor()
Returns the number of arguments enqueued per 3D tensor object.
Definition: ICLKernel.h:214
BorderSize border_size() const override
The size of the border for that kernel.
#define ARM_COMPUTE_UNUSED(...)
To avoid unused variables warnings.
Definition: Error.h:152
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:68
bool is_data_type_quantized_per_channel(DataType dt)
Check if a given data type is of per channel type.
Definition: Utils.h:1245
std::string float_to_string_with_full_precision(float val)
Create a string with the float in full precision.
Definition: Utils.h:1262
std::pair< int32_t, int32_t > get_quantized_activation_min_max(ActivationLayerInfo act_info, DataType data_type, UniformQuantizationInfo oq_info)
Returns a pair of minimum and maximum values for a quantized activation.
Definition: Utils.cpp:483
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
quantized, asymmetric fixed-point 8-bit number unsigned
std::pair< unsigned int, unsigned int > stride() const
Get the stride.
Definition: Types.h:770
void configure(const ICLTensor *input, const ICLTensor *weights, const ICLTensor *biases, ICLTensor *output, const PadStrideInfo &conv_info, unsigned int depth_multiplier=1, ActivationLayerInfo act_info=ActivationLayerInfo(), const Size2D &dilation=Size2D(1U, 1U), const ICLTensor *output_multipliers=nullptr, const ICLTensor *output_shifts=nullptr) override
Default move assignment operator.
std::string kernel_name
std::string get_cl_type_from_data_type(const DataType &dt)
Translates a tensor data type to the appropriate OpenCL type.
Definition: CLHelpers.cpp:37
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&#39;s metadata.
unsigned int pad_right() const
Get the right padding.
Definition: Types.h:801
void add_option_if(bool cond, std::string option)
Adds option if a given condition is true;.
Padding and stride information class.
Definition: Types.h:722
virtual size_t element_size() const =0
Element size in bytes calculated as data_size() * num_channels()
void set(size_t dimension, const Dimension &dim)
Set the values of a given dimension.
Definition: Window.inl:49
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:206
static constexpr unsigned int num_arguments_per_4D_tensor()
Returns the number of arguments enqueued per 4D tensor object.
Definition: ICLKernel.h:222
#define ARM_COMPUTE_ERROR_ON_UNCONFIGURED_KERNEL(k)
Definition: Validate.h:941
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:528
Num samples, channels, height, width.
CLCompileContext class.
src_info set_data_layout(data_layout)
bool is_data_type_quantized_asymmetric(DataType dt)
Check if a given data type is of asymmetric quantized type.
Definition: Utils.h:1190
std::string get_cl_promoted_type_from_data_type(const DataType &dt)
Translates a tensor data type to the appropriate OpenCL promoted type.
Definition: CLHelpers.cpp:73
void set_dimension_step(size_t dimension, int step)
Set the step of a given dimension.
Definition: Window.inl:167
void add_2D_tensor_argument(unsigned int &idx, const ICLTensor *tensor, const Window &window)
Add the passed 2D tensor&#39;s parameters to the object&#39;s kernel&#39;s arguments starting from the index idx...
Definition: ICLKernel.h:148
ScaleKernelInfo info(interpolation_policy, default_border_mode, PixelValue(), sampling_policy, false)
Interface for OpenCL tensor.
Definition: ICLTensor.h:42
#define ARM_COMPUTE_CREATE_ERROR(error_code, msg)
Creates an error with a given message.
Definition: Error.h:159
static constexpr size_t DimZ
Alias for dimension 2 also known as Z dimension.
Definition: Window.h:47
Manages all the OpenCL kernels compilation and caching, provides accessors for the OpenCL Context...
Class for specifying the size of an image or rectangle.
Definition: Size2D.h:34
#define ARM_COMPUTE_RETURN_ERROR_ON_MISMATCHING_DATA_TYPES(...)
Definition: Validate.h:545
#define ARM_COMPUTE_RETURN_ERROR_ON_DATA_TYPE_CHANNEL_NOT_IN(t, c,...)
Definition: Validate.h:792
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:513
Status validate_arguments(const ITensorInfo *input, const ITensorInfo *bias, const ITensorInfo *output, const GEMMLowpOutputStageInfo *output_stage)
Window first_slice_window_4D() const
First 4D slice of the window.
Definition: Window.h:299
bool slide_window_slice_4D(Window &slice) const
Slide the passed 4D window slice.
Definition: Window.h:347
#define ARM_COMPUTE_RETURN_ERROR_ON_MSG(cond, msg)
If the condition is true, an error is returned.
Definition: Error.h:244
#define ARM_COMPUTE_ERROR_ON_NULLPTR(...)
Definition: Validate.h:161
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:1358
quantized, asymmetric fixed-point 8-bit number signed
void add_1D_tensor_argument(unsigned int &idx, const ICLTensor *tensor, const Window &window)
Add the passed 1D tensor&#39;s parameters to the object&#39;s kernel&#39;s arguments starting from the index idx...
Definition: ICLKernel.h:124
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:182
unsigned int pad_left() const
Get the left padding.
Definition: Types.h:796
Describe a multidimensional execution window.
Definition: Window.h:39
#define ARM_COMPUTE_ERROR_ON_INVALID_SUBWINDOW(f, s)
Definition: Validate.h:205
SimpleTensor< T > slice(const SimpleTensor< T > &src, Coordinates starts, Coordinates ends)
constexpr const Dimension & x() const
Alias to access the first dimension of the window.
Definition: Window.h:145