24.02.1
|
#include "arm_compute/dynamic_fusion/runtime/gpu/cl/ClWorkloadRuntime.h"
#include "arm_compute/core/experimental/Types.h"
#include "arm_compute/runtime/CL/CLTensor.h"
#include "src/dynamic_fusion/runtime/gpu/cl/ClKernelRuntime.h"
#include "src/dynamic_fusion/sketch/gpu/GpuWorkloadSketchImpl.h"
#include "src/dynamic_fusion/sketch/gpu/GpuWorkloadSourceCode.h"
#include "support/Cast.h"
#include <algorithm>
Go to the source code of this file.
Namespaces | |
arm_compute | |
Copyright (c) 2017-2024 Arm Limited. | |
arm_compute::experimental | |
arm_compute::experimental::dynamic_fusion | |
AuxMemoryInfo memory_info {} |
Memory requirement.
Definition at line 69 of file ClWorkloadRuntime.cpp.
CLTensor* tensor {} |
Pointer to the auxiliary tensor.
Definition at line 67 of file ClWorkloadRuntime.cpp.
Referenced by PPMWriter::access_tensor(), DummyAccessor::access_tensor(), NumPyAccessor::access_tensor(), SaveNumPyAccessor::access_tensor(), ImageAccessor::access_tensor(), ValidationInputAccessor::access_tensor(), ValidationOutputAccessor::access_tensor(), VerifyAccessor< D >::access_tensor(), DetectionOutputAccessor::access_tensor(), TopNPredictionsAccessor::access_tensor(), RandomAccessor::access_tensor(), NumPyBinLoader::access_tensor(), Accessor::Accessor(), AclCreateTensor(), AclDestroyTensor(), AclGetClMem(), AclGetTensorDescriptor(), AclGetTensorSize(), AclMapTensor(), AclTensorImport(), AclUnmapTensor(), TensorPack::add(), ICLKernel::add_1D_tensor_argument(), ICLKernel::add_1D_tensor_argument_if(), ICLKernel::add_2D_tensor_argument(), ICLKernel::add_2D_tensor_argument_if(), ICLKernel::add_3D_tensor_argument(), ICLKernel::add_3d_tensor_nhw_argument(), ICLKernel::add_4D_tensor_argument(), ICLKernel::add_4d_tensor_nhwc_argument(), ICLKernel::add_5D_tensor_argument(), ITensorPack::add_const_tensor(), ArgumentPack< arm_compute::ITensorInfo >::add_const_tensor(), arm_compute::test::validation::add_padding_x(), ITensorPack::add_tensor(), TensorPack::add_tensor(), ArgumentPack< arm_compute::ITensorInfo >::add_tensor(), ICLKernel::add_tensor_argument(), arm_compute::graph::detail::allocate_all_input_tensors(), arm_compute::graph::detail::allocate_all_output_tensors(), arm_compute::graph::detail::allocate_all_tensors(), DependencyGraph::build_operators_sequence(), arm_compute::misc::shape_calculator::calculate_concatenate_shape(), arm_compute::graph::detail::call_tensor_accessor(), arm_compute::experimental::dynamic_fusion::cl_add_tensor_component_argument(), CLAccessor::CLAccessor(), CLAuxTensorHandler::CLAuxTensorHandler(), CpuFill::configure(), ClFill::configure(), CpuFillKernel::configure(), ClFillKernel::configure(), NEFill::configure(), NEFillBorderKernel::configure(), CLFill::configure(), CLFillBorderKernel::configure(), arm_compute::graph::detail::configure_all_tensors(), arm_compute::graph::configure_tensor(), arm_compute::test::copy_tensor(), CpuAuxTensorHandler::CpuAuxTensorHandler(), arm_compute::create_image2d_from_tensor(), NEDeviceBackend::create_tensor(), CpuContext::create_tensor(), CLDeviceBackend::create_tensor(), ClContext::create_tensor(), arm_compute::test::create_tensor(), VerifyAccessor< D >::create_tensors(), GpuCkwVariableTable::declare_variable(), GpuKernelVariableTable::declare_variable(), arm_compute::test::validation::reference::depthconcatenate_layer(), arm_compute::utils::draw_detection_rectangle(), DependencyGraph::dst_ops_from_tensor(), arm_compute::error_on_data_layout_not_in(), arm_compute::error_on_data_type_channel_not_in(), arm_compute::error_on_data_type_not_in(), arm_compute::error_on_mismatching_data_layouts(), arm_compute::error_on_mismatching_data_types(), arm_compute::error_on_tensor_not_2d(), arm_compute::error_on_tensors_not_even(), arm_compute::error_on_tensors_not_subsampled(), arm_compute::error_on_unsupported_cpu_bf16(), arm_compute::error_on_unsupported_cpu_fp16(), arm_compute::error_on_unsupported_fp16(), arm_compute::export_to_cl_image(), arm_compute::test::validation::utils::fill(), AssetsLibrary::fill(), AssetsLibrary::fill_borders_with_garbage(), AssetsLibrary::fill_boxes(), AssetsLibrary::fill_layer_data(), IImageLoader::fill_planar_tensor(), arm_compute::utils::fill_random_tensor(), AssetsLibrary::fill_static_values(), NPYLoader::fill_tensor(), VerifyAccessor< D >::fill_tensor(), AssetsLibrary::fill_tensor_uniform(), AssetsLibrary::fill_tensor_uniform_ranged(), AssetsLibrary::fill_tensor_value(), arm_compute::utils::fill_tensor_value(), arm_compute::utils::fill_tensor_vector(), arm_compute::utils::fill_tensor_zero(), arm_compute::test::fill_tensors(), AssetsLibrary::fill_with_generator(), GpuKernelComponentGroup::finalize(), arm_compute::graph::force_target_to_graph(), arm_compute::utils::get_accessor(), arm_compute::graph::backends::detail::get_backing_tensor(), arm_compute::graph::backends::detail::get_backing_tensor_info(), ArgumentPack< arm_compute::ITensorInfo >::get_const_dst_tensors(), ArgumentPack< arm_compute::ITensorInfo >::get_const_src_tensors(), ArgumentPack< arm_compute::ITensorInfo >::get_dst_tensors(), arm_compute::get_internal(), arm_compute::get_padding_info(), ArgumentPack< arm_compute::ITensorInfo >::get_src_tensors(), arm_compute::graph::get_tensor_descriptor(), GpuKernelComponentGroup::get_tile_for_tensor(), GpuKernelVariableTable::get_variable(), GpuKernelVariableTable::get_variable_list(), NPYLoader::init_tensor(), GpuKernelComponentGroup::is_input_tensor(), GpuKernelComponentGroup::is_intermediate_tensor(), Iterator::Iterator(), arm_compute::utils::load_trained_data(), arm_compute::manage_workspace(), arm_compute::utils::map(), get_tensor_info_t< ITensorInfo * >::operator()(), arm_compute::test::operator<<(), SimpleTensor< uint8_t >::operator=(), RawTensor::operator=(), VerifyAccessor< D >::output_shape(), CaffePreproccessor::preprocess(), TFPreproccessor::preprocess(), RawTensor::RawTensor(), arm_compute::release_temporaries(), arm_compute::graph::detail::release_unused_tensors(), ClKernelRuntime::run_op(), ClFillKernel::run_op(), CLFillBorderKernel::run_op(), arm_compute::utils::save_to_npy(), arm_compute::utils::save_to_ppm(), arm_compute::graph::set_tensor_accessor(), SimpleTensor< uint8_t >::SimpleTensor(), SimpleTensorAccessor< T >::SimpleTensorAccessor(), DependencyGraph::src_ops_from_tensor(), arm_compute::test::sync_tensor_if_necessary(), Tensor::Tensor(), tensor3D_index2ptr(), tensor3D_offset(), tensor3D_ptr_no_update(), tensor4D_offset(), arm_compute::test::validation::TEST_CASE(), arm_compute::test::to_string(), arm_compute::to_string(), arm_compute::utils::unmap(), examples::gemm_tuner_helpers::update_padding_for_cl_image(), arm_compute::opencl::kernels::gemm::update_padding_for_cl_image(), update_tensor3D_workitem_ptr(), update_tensor4D_workitem_no_step_ptr(), update_tensor4D_workitem_ptr(), ClFill::validate(), ClFillKernel::validate(), CLFill::validate(), arm_compute::test::validation::validate(), VerifyAccessor< D >::validate(), arm_compute::detail::validate_internal_tensor(), and arm_compute::test::validation::validate_wrap().
TensorInfo tensor_info {} |
Associated tensor info.
Definition at line 68 of file ClWorkloadRuntime.cpp.
Referenced by arm_compute::test::validation::compute_float_reference(), NENormalizationLayer::configure(), GpuWorkloadContext::Impl::create_auxiliary_tensor(), GpuWorkloadSketch::Implementation::create_auxiliary_tensor(), GpuWorkloadContext::create_tensor_info(), GpuWorkloadContext::Impl::create_virtual_tensor(), arm_compute::error_on_data_layout_not_in(), arm_compute::error_on_data_type_channel_not_in(), arm_compute::error_on_data_type_not_in(), arm_compute::error_on_mismatching_data_layouts(), arm_compute::error_on_mismatching_data_types(), arm_compute::error_on_mismatching_quantization_info(), arm_compute::error_on_mismatching_shapes(), arm_compute::error_on_unsupported_cpu_bf16(), arm_compute::error_on_unsupported_cpu_fp16(), arm_compute::error_on_unsupported_fp16(), NPYLoader::init_tensor(), arm_compute::experimental::dynamic_fusion::is_alloc_tensor(), arm_compute::experimental::dynamic_fusion::is_invalid_tensor(), arm_compute::experimental::dynamic_fusion::is_noalloc_tensor(), arm_compute::experimental::dynamic_fusion::is_valid_tensor(), GpuWorkloadContext::Impl::register_user_tensor(), arm_compute::helpers::tensor_info::tensors_have_different_quantization_info(), arm_compute::test::validation::TEST_CASE(), and arm_compute::experimental::dynamic_fusion::to_ckw().