24.02.1
|
#include "src/gpu/cl/kernels/ClIm2ColKernel.h"
#include "arm_compute/core/CL/CLHelpers.h"
#include "arm_compute/core/CL/CLKernelLibrary.h"
#include "arm_compute/core/CL/ICLTensor.h"
#include "arm_compute/core/CL/OpenCL.h"
#include "arm_compute/core/Helpers.h"
#include "arm_compute/core/TensorInfo.h"
#include "arm_compute/core/utils/misc/ShapeCalculator.h"
#include "arm_compute/core/utils/StringUtils.h"
#include "arm_compute/core/Validate.h"
#include "src/core/AccessWindowStatic.h"
#include "src/core/CL/CLValidate.h"
#include "src/core/helpers/AutoConfiguration.h"
#include "src/core/helpers/WindowHelpers.h"
#include "support/Cast.h"
#include "support/StringSupport.h"
#include <cmath>
#include <tuple>
#include <utility>
Go to the source code of this file.
Namespaces | |
arm_compute | |
Copyright (c) 2017-2024 Arm Limited. | |
arm_compute::opencl | |
Interface to convert the 2D Fully Connected weights from NCHW to NHWC or vice versa. | |
arm_compute::opencl::kernels | |
std::set<std::string> build_options {} |
Definition at line 59 of file ClIm2ColKernel.cpp.
Referenced by Program::build(), ClTransposedConvolutionKernel::configure(), ClIndirectConv2dAddressPrecalculationKernel::configure(), ClIndirectConv2dKernel::configure(), ClDirectConv2dKernel::configure(), ClDirectConv3dKernel::configure(), and CLCompileContext::create_kernel().
bool is_padding_required_nchw {} |
Definition at line 61 of file ClIm2ColKernel.cpp.
std::string kernel_name {} |
Definition at line 58 of file ClIm2ColKernel.cpp.
Referenced by clCreateKernel(), ClTransposedConvolutionKernel::configure(), ClDequantizeKernel::configure(), ClElementWiseUnaryKernel::configure(), ClWidthConcatenate2TensorsKernel::configure(), ClMatMulLowpNativeMMULKernel::configure(), ClPool3dKernel::configure(), ClPool2dKernel::configure(), ClScaleKernel::configure(), ClWidthConcatenateKernel::configure(), ClHeightConcatenateKernel::configure(), ClWidthConcatenate4TensorsKernel::configure(), ClActivationKernel::configure(), CpuSoftmaxKernel::configure(), ClMatMulNativeKernel::configure(), ClDepthConcatenateKernel::configure(), ClBatchConcatenateKernel::configure(), ClMatMulLowpNativeKernel::configure(), ClGemmLowpMatrixMultiplyNativeKernel::configure(), ClGemmReshapeLhsMatrixKernel::configure(), CLMaxUnpoolingLayerKernel::configure(), ClGemmMatrixMultiplyNativeKernel::configure(), CLBitwiseKernel::configure(), CLChannelShuffleLayerKernel::configure(), ClWinogradFilterTransformKernel::configure(), ClWinogradInputTransformKernel::configure(), ClGemmLowpQuantizeDownInt32ScaleByFixedPointKernel::configure(), ClGemmMatrixMultiplyReshapedOnlyRhsMMULKernel::configure(), ClIndirectConv2dAddressPrecalculationKernel::configure(), CLSelectKernel::configure(), ClIndirectConv2dKernel::configure(), ClWinogradOutputTransformKernel::configure(), ClGemmLowpQuantizeDownInt32ScaleByFloatKernel::configure(), ClGemmLowpQuantizeDownInt32ScaleKernel::configure(), CLComputeAllAnchorsKernel::configure(), ClSoftmaxKernel::configure(), CLFFTScaleKernel::configure(), CLNormalizationLayerKernel::configure(), ClCastKernel::configure(), ClGemmLowpMatrixMultiplyReshapedKernel::configure(), CLComparisonKernel::configure(), CLFFTDigitReverseKernel::configure(), ClGemmLowpOffsetContributionKernel::configure(), ClGemmLowpOffsetContributionOutputStageKernel::configure(), CLReorgLayerKernel::configure(), ClGemmReshapeRhsMatrixKernel::configure(), CLNormalizePlanarYUVLayerKernel::configure(), CLRangeKernel::configure(), ClDirectConv2dKernel::configure(), CLFFTRadixStageKernel::configure(), ClDirectConv3dKernel::configure(), ClGemmLowpMatrixMultiplyReshapedOnlyRhsKernel::configure(), CLL2NormalizeLayerKernel::configure(), CLPadLayerKernel::configure(), ClMatMulNativeMMULKernel::configure(), ClMulKernel::configure(), CLBoundingBoxTransformKernel::configure(), CLDepthwiseConvolutionLayerNativeKernel::configure(), ClGemmMatrixMultiplyReshapedOnlyRhsKernel::configure(), CLROIPoolingLayerKernel::configure(), ClGemmLowpMatrixAReductionKernel::configure(), CLROIAlignLayerKernel::configure(), CLFillBorderKernel::configure(), ClGemmMatrixMultiplyReshapedKernel::configure(), ClGemmLowpMatrixBReductionKernel::configure(), CLKernelLibrary::create_kernel(), CLCompileContext::create_kernel(), arm_compute::create_kernel(), ClTemplateCast::get_component_code(), GpuCkwMatMul::get_name(), CLKernelLibrary::get_program_name(), GpuCkwDriver::GpuCkwDriver(), ClKernelLibrary::program_name(), arm_compute::save_program_cache_to_file(), and arm_compute::test::validation::TEST_CASE().
unsigned int num_elems_processed_per_iteration {} |
Definition at line 60 of file ClIm2ColKernel.cpp.
Referenced by ClElementWiseUnaryKernel::configure(), ClWidthConcatenate2TensorsKernel::configure(), ClHeightConcatenateKernel::configure(), ClWidthConcatenateKernel::configure(), ClWidthConcatenate4TensorsKernel::configure(), ClActivationKernel::configure(), ClBatchConcatenateKernel::configure(), ClDepthConcatenateKernel::configure(), ICLSimpleKernel::configure(), NEBitwiseNotKernel::configure(), CLInstanceNormalizationLayerKernel::configure(), NEBitwiseAndKernel::configure(), NEBitwiseOrKernel::configure(), ClGemmLowpQuantizeDownInt32ScaleByFixedPointKernel::configure(), NEBitwiseXorKernel::configure(), ClGemmLowpQuantizeDownInt32ScaleKernel::configure(), CLDeconvolutionLayerUpsampleKernel::configure(), ClGemmLowpQuantizeDownInt32ScaleByFloatKernel::configure(), CLQLSTMLayerNormalizationKernel::configure(), CLComparisonKernel::configure(), ClCastKernel::configure(), CLMeanStdDevNormalizationKernel::configure(), ClGemmLowpOffsetContributionOutputStageKernel::configure(), ClGemmLowpOffsetContributionKernel::configure(), CLNormalizePlanarYUVLayerKernel::configure(), CLRangeKernel::configure(), CLBoundingBoxTransformKernel::configure(), CLBatchNormalizationLayerKernel::configure(), CLComputeMeanVariance::configure(), ClGemmLowpMatrixBReductionKernel::configure(), CpuGemmLowpMatrixBReductionKernel::configure(), GpuCkwCast::get_window(), GpuCkwElementwiseBinary::get_window(), GpuCkwActivation::get_window(), CpuSoftmaxKernel::run_op(), and CpuPool2dKernel::validate().