24.02.1
|
Data Structures | |
struct | ActivationDataTypeISASelectorData |
struct | CastDataTypeISASelectorData |
class | CpuActivationKernel |
Interface for the activation kernel. More... | |
class | CpuAddKernel |
Interface for the kernel to perform addition between two tensors. More... | |
struct | CpuAddKernelDataTypeISASelectorData |
class | CpuAddMulAddKernel |
Interface for the kernel to perform addition between two tensors. More... | |
class | CpuArithmeticKernel |
class | CpuCastKernel |
Casts a given tensor to a new type. More... | |
class | CpuCol2ImKernel |
Kernel to perform col2im reshaping. More... | |
class | CpuComparisonKernel |
class | CpuComplexMulKernel |
Interface for the complex pixelwise multiplication kernel. More... | |
class | CpuConcatenateBatchKernel |
Interface for the batch concatenate kernel. More... | |
class | CpuConcatenateDepthKernel |
Interface for the depth concatenate kernel. More... | |
class | CpuConcatenateHeightKernel |
Interface for the height concatenate kernel. More... | |
class | CpuConcatenateWidthKernel |
Interface for the width concatenate kernel. More... | |
class | CpuConvertFullyConnectedWeightsKernel |
Interface to convert the 2D Fully Connected weights from NCHW to NHWC or vice versa. More... | |
class | CpuConvertQuantizedSignednessKernel |
Kernel to convert asymmetric signed to asymmetric signed and vice-versa. More... | |
class | CpuCopyKernel |
Kernel to perform a copy between two tensors. More... | |
class | CpuDepthwiseConv2dAssemblyWrapperKernel |
This class is a wrapper for the depthwise convolution assembly kernels. More... | |
class | CpuDepthwiseConv2dNativeKernel |
Interface for the kernel to run a depthwise convolution native on a tensor. More... | |
class | CpuDequantizeKernel |
Interface for the dequantization layer kernel. More... | |
class | CpuDirectConv2dKernel |
Interface for the kernel to perform Direct Convolution Layer. More... | |
class | CpuDirectConv2dOutputStageKernel |
Kernel to accumulate the biases, if provided, or downscale in case of quantized input. More... | |
class | CpuDirectConv3dKernel |
Interface for the kernel to perform 3D Direct Convolution Layer. More... | |
class | CpuDivisionKernel |
class | CpuElementwiseKernel |
Interface for an element-wise operation kernel. More... | |
class | CpuElementwiseUnaryKernel |
Interface for an element-wise unary operation kernel. More... | |
class | CpuFillKernel |
Kernel for filling a tensor with a given constant value. More... | |
class | CpuFloorKernel |
Cpu accelarated kernel to perform a floor operation. More... | |
class | CpuGemmInterleave4x4Kernel |
Kernel to interleave the elements of a matrix. More... | |
class | CpuGemmLowpMatrixAReductionKernel |
Kernel used to compute the row-vectors of sums of all the entries in each row of Matrix A. More... | |
class | CpuGemmLowpMatrixBReductionKernel |
Kernel used to compute the row-vectors of sums of all the entries in each column of Matrix B. More... | |
class | CpuGemmLowpMatrixMultiplyKernel |
Kernel to multiply matrices. More... | |
class | CpuGemmLowpOffsetContributionKernel |
Kernel used to add the offset contribution after CpuGemmLowpMatrixMultiplyKernel. More... | |
class | CpuGemmLowpOffsetContributionOutputStageKernel |
Kernel used to add the offset contribution and perform the output stage after CpuGemmLowpMatrixMultiplyKernel. More... | |
class | CpuGemmLowpQuantizeDownInt32ScaleKernel |
Kernel used to quantize down the int32 accumulator values of GEMMLowp to QASYMM8/QASYMM8_SIGNED. More... | |
class | CpuGemmLowpQuantizeDownInt32ToInt16ScaleByFixedPointKernel |
Kernel used to quantize down the int32 accumulator values of GEMMLowp to QSYMM16. More... | |
class | CpuGemmLowpQuantizeDownInt32ToInt8ScaleByFixedPointKernel |
Kernel used to quantize down the int32 accumulator values of GEMMLowp to QASYMM8_SIGNED. More... | |
class | CpuGemmLowpQuantizeDownInt32ToUint8ScaleByFixedPointKernel |
Kernel used to quantize down the int32 accumulator values of GEMMLowp to QASYMM8. More... | |
class | CpuGemmMatrixAdditionKernel |
Kernel to perform the in-place matrix addition between 2 matrices taking into account that the second matrix might be weighted by a scalar value beta: More... | |
class | CpuGemmMatrixMultiplyKernel |
Kernel to multiply two input matrices "A" and "B". More... | |
class | CpuGemmTranspose1xWKernel |
Kernel which transposes the elements of a matrix in chunks of 1xW, where W is equal to (16 / element size of the tensor) More... | |
class | CpuIm2ColKernel |
Interface for the im2col reshape kernel. More... | |
class | CpuMaxUnpoolingLayerKernel |
Interface for the pooling layer kernel. More... | |
class | CpuMulKernel |
Interface for the kernel to perform multiplication between two tensors. More... | |
class | CpuPermuteKernel |
Kernel to perform tensor permutation given a permutation vector. More... | |
class | CpuPool2dAssemblyWrapperKernel |
This class is a wrapper for the assembly kernels. More... | |
class | CpuPool2dKernel |
Interface for the pooling layer kernel. More... | |
class | CpuPool3dKernel |
Interface for the kernel to perform Pooling 3D. More... | |
class | CpuPowerKernel |
class | CpuQuantizeKernel |
Interface for the quantization layer kernel. More... | |
class | CpuReshapeKernel |
Interface for the kernel to perform tensor reshaping. More... | |
class | CpuScaleKernel |
Arm(R) Neon(TM) kernel to perform scaling on a tensor. More... | |
class | CpuSoftmaxKernel |
Interface for softmax computation. More... | |
class | CpuSubKernel |
Interface for the kernel to perform subtraction between two tensors. More... | |
class | CpuTransposeKernel |
Kernel which transposes the elements of a matrix. More... | |
class | CpuWeightsReshapeKernel |
Kernel to perform reshaping on the weights used by convolution and locally connected layer. More... | |
struct | DataTypeDataLayoutISASelectorData |
struct | DataTypeISASelectorData |
struct | DepthwiseConv2dNativeDataTypeISASelectorData |
struct | ElementwiseDataTypeISASelectorData |
struct | PoolDataTypeISASelectorData |
struct | ScaleKernelDataTypeISASelectorData |
struct | SoftmaxKernelDataTypeISASelectorData |
Functions | |
Status | validate_arguments (const ITensorInfo *src, const ITensorInfo *weights, const ITensorInfo *dst, const PadStrideInfo &conv_info) |
std::pair< Status, Window > | validate_and_configure_window (ITensorInfo *src, ITensorInfo *dst) |
void | run_im2col_fp32_pad (const ITensor *src, ITensor *dst, const Window &window, DataLayout data_layout, const PadStrideInfo &conv_info, std::pair< unsigned int, unsigned int > convolved_dims, const Size2D &kernel_dims, const Size2D &dilation, uint32_t input_pad_right, bool has_bias) |
void | run_im2col_fp32_nopad (const ITensor *src, ITensor *dst, const Window &window, DataLayout data_layout, const PadStrideInfo &conv_info, std::pair< unsigned int, unsigned int > convolved_dims, const Size2D &kernel_dims, const Size2D &dilation, uint32_t input_pad_right, bool has_bias) |
void | run_im2col_int8_nopad_nhwc (const ITensor *src, ITensor *dst, const Window &window, DataLayout data_layout, const PadStrideInfo &conv_info, std::pair< unsigned int, unsigned int > convolved_dims, const Size2D &kernel_dims, const Size2D &dilation, uint32_t input_pad_right, bool has_bias) |
void | run_im2col_uint8_nopad_nhwc (const ITensor *src, ITensor *dst, const Window &window, DataLayout data_layout, const PadStrideInfo &conv_info, std::pair< unsigned int, unsigned int > convolved_dims, const Size2D &kernel_dims, const Size2D &dilation, uint32_t input_pad_right, bool has_bias) |
void | run_im2col_qasymm8_pad_nhwc (const ITensor *src, ITensor *dst, const Window &window, DataLayout data_layout, const PadStrideInfo &conv_info, std::pair< unsigned int, unsigned int > convolved_dims, const Size2D &kernel_dims, const Size2D &dilation, uint32_t input_pad_right, bool has_bias) |
void | internal_run_im2col_fp16_pad (const ITensor *src, ITensor *dst, const Window &window, DataLayout data_layout, const PadStrideInfo &conv_info, std::pair< unsigned int, unsigned int > convolved_dims, const Size2D &kernel_dims, const Size2D &dilation, uint32_t input_pad_right, bool has_bias) |
void | internal_run_im2col_fp16_nopad (const ITensor *src, ITensor *dst, const Window &window, DataLayout data_layout, const PadStrideInfo &conv_info, std::pair< unsigned int, unsigned int > convolved_dims, const Size2D &kernel_dims, const Size2D &dilation, uint32_t input_pad_right, bool has_bias) |
void | internal_run_im2col_fp16_nchw_pad (const ITensor *src, ITensor *dst, const Window &window, DataLayout data_layout, const PadStrideInfo &conv_info, std::pair< unsigned int, unsigned int > convolved_dims, const Size2D &kernel_dims, const Size2D &dilation, uint32_t input_pad_right, bool has_bias) |
void | internal_run_im2col_fp16_nchw_nopad (const ITensor *src, ITensor *dst, const Window &window, DataLayout data_layout, const PadStrideInfo &conv_info, std::pair< unsigned int, unsigned int > convolved_dims, const Size2D &kernel_dims, const Size2D &dilation, uint32_t input_pad_right, bool has_bias) |
template<typename T , bool has_pads> | |
void | linearize_volume_nchw (const uint8_t *const in_ptr, T *out_ptr, bool has_bias, int top_left_x, int top_left_y, int kernel_width, int kernel_height, int kernel_depth, int input_w, int input_h, int input_stride_x, int input_stride_y, int input_stride_z, int pad_value, int dilation_x, int dilation_y) |
template<typename T , bool has_pads> | |
void | linearize_volume_nhwc (const uint8_t *const in_ptr, T *out_ptr, bool has_bias, int start_x, int start_y, int kernel_width, int kernel_height, int input_w, int input_h, int input_c, int input_stride_y, int input_stride_z, int pad_value, int dilation_x, int dilation_y) |
template<typename T , bool has_pads> | |
void | linearize_volume_nhwc (const uint8_t *const in_ptr, T *out_ptr, bool has_bias, int start_x, int start_y, int kernel_width, int kernel_height, int input_w, int input_h, int input_c, int input_stride_y, int input_stride_z, int pad_value, int dilation_x, int dilation_y, int pad_right) |
template<typename T , bool has_pads, bool is_nchw> | |
void | run_im2col (const ITensor *src, ITensor *dst, const Window &window, DataLayout data_layout, const PadStrideInfo &conv_info, std::pair< unsigned int, unsigned int > convolved_dims, const Size2D &kernel_dims, const Size2D &dilation, uint32_t input_pad_right, bool has_bias) |
void | neon_fp32_nhwc_directconv2d (const Window &window, const ITensor *src, const ITensor *weights, ITensor *dst, const PadStrideInfo &conv_info) |
void | neon_fp16_nchw_directconv2d (const Window &window, const ITensor *src, const ITensor *weights, ITensor *dst, const PadStrideInfo &conv_info) |
void | neon_fp32_nchw_directconv2d (const Window &window, const ITensor *src, const ITensor *weights, ITensor *dst, const PadStrideInfo &conv_info) |
void | run_im2col_fp32_nchw_pad (const ITensor *src, ITensor *dst, const Window &window, DataLayout data_layout, const PadStrideInfo &conv_info, std::pair< unsigned int, unsigned int > convolved_dims, const Size2D &kernel_dims, const Size2D &dilation, uint32_t input_pad_right, bool has_bias) |
void | run_im2col_fp32_nchw_nopad (const ITensor *src, ITensor *dst, const Window &window, DataLayout data_layout, const PadStrideInfo &conv_info, std::pair< unsigned int, unsigned int > convolved_dims, const Size2D &kernel_dims, const Size2D &dilation, uint32_t input_pad_right, bool has_bias) |
void | run_im2col_fp16_nchw_pad (const ITensor *src, ITensor *dst, const Window &window, DataLayout data_layout, const PadStrideInfo &conv_info, std::pair< unsigned int, unsigned int > convolved_dims, const Size2D &kernel_dims, const Size2D &dilation, uint32_t input_pad_right, bool has_bias) |
void | run_im2col_fp16_nchw_nopad (const ITensor *src, ITensor *dst, const Window &window, DataLayout data_layout, const PadStrideInfo &conv_info, std::pair< unsigned int, unsigned int > convolved_dims, const Size2D &kernel_dims, const Size2D &dilation, uint32_t input_pad_right, bool has_bias) |
void | run_im2col_bf16_nchw_pad (const ITensor *src, ITensor *dst, const Window &window, DataLayout data_layout, const PadStrideInfo &conv_info, std::pair< unsigned int, unsigned int > convolved_dims, const Size2D &kernel_dims, const Size2D &dilation, uint32_t input_pad_right, bool has_bias) |
void | run_im2col_bf16_nchw_nopad (const ITensor *src, ITensor *dst, const Window &window, DataLayout data_layout, const PadStrideInfo &conv_info, std::pair< unsigned int, unsigned int > convolved_dims, const Size2D &kernel_dims, const Size2D &dilation, uint32_t input_pad_right, bool has_bias) |
void | run_im2col_qasymm8_nchw_pad (const ITensor *src, ITensor *dst, const Window &window, DataLayout data_layout, const PadStrideInfo &conv_info, std::pair< unsigned int, unsigned int > convolved_dims, const Size2D &kernel_dims, const Size2D &dilation, uint32_t input_pad_right, bool has_bias) |
void | run_im2col_qasymm8_nchw_nopad (const ITensor *src, ITensor *dst, const Window &window, DataLayout data_layout, const PadStrideInfo &conv_info, std::pair< unsigned int, unsigned int > convolved_dims, const Size2D &kernel_dims, const Size2D &dilation, uint32_t input_pad_right, bool has_bias) |
void | run_im2col_fp16_pad (const ITensor *src, ITensor *dst, const Window &window, DataLayout data_layout, const PadStrideInfo &conv_info, std::pair< unsigned int, unsigned int > convolved_dims, const Size2D &kernel_dims, const Size2D &dilation, uint32_t input_pad_right, bool has_bias) |
void | run_im2col_fp16_nopad (const ITensor *src, ITensor *dst, const Window &window, DataLayout data_layout, const PadStrideInfo &conv_info, std::pair< unsigned int, unsigned int > convolved_dims, const Size2D &kernel_dims, const Size2D &dilation, uint32_t input_pad_right, bool has_bias) |
void | run_im2col_bf16_pad (const ITensor *src, ITensor *dst, const Window &window, DataLayout data_layout, const PadStrideInfo &conv_info, std::pair< unsigned int, unsigned int > convolved_dims, const Size2D &kernel_dims, const Size2D &dilation, uint32_t input_pad_right, bool has_bias) |
void | run_im2col_bf16_nopad (const ITensor *src, ITensor *dst, const Window &window, DataLayout data_layout, const PadStrideInfo &conv_info, std::pair< unsigned int, unsigned int > convolved_dims, const Size2D &kernel_dims, const Size2D &dilation, uint32_t input_pad_right, bool has_bias) |
template<typename T > | |
void | convolve_nchw (const Window &window, const ITensor *src, const ITensor *weights, ITensor *dst, const PadStrideInfo &conv_info) |
template<typename T > | |
void | convolve_nhwc (const Window &window, const ITensor *src, const ITensor *weights, ITensor *dst, const PadStrideInfo &conv_info) |
template void | convolve_nhwc< float > (const Window &window, const ITensor *src, const ITensor *weights, ITensor *dst, const PadStrideInfo &conv_info) |
void | run_im2col_qasymm8_pad (const ITensor *src, ITensor *dst, const Window &window, DataLayout data_layout, const PadStrideInfo &conv_info, std::pair< unsigned int, unsigned int > convolved_dims, const Size2D &kernel_dims, const Size2D &dilation, uint32_t input_pad_right, bool has_bias) |
void | run_im2col_qasymm8_nopad (const ITensor *src, ITensor *dst, const Window &window, DataLayout data_layout, const PadStrideInfo &conv_info, std::pair< unsigned int, unsigned int > convolved_dims, const Size2D &kernel_dims, const Size2D &dilation, uint32_t input_pad_right, bool has_bias) |
using ActivationDataTypeISASelectorDataPtr = std::add_pointer<bool(const ActivationDataTypeISASelectorData &data)>::type |
Definition at line 118 of file CpuKernelSelectionTypes.h.
using CastDataTypeISASelectorDataPtr = std::add_pointer<bool(const CastDataTypeISASelectorData &data)>::type |
Definition at line 116 of file CpuKernelSelectionTypes.h.
using CpuAddKernelDataTypeISASelectorDataPtr = std::add_pointer<bool(const CpuAddKernelDataTypeISASelectorData &data)>::type |
Definition at line 120 of file CpuKernelSelectionTypes.h.
using DataTypeDataLayoutSelectorPtr = std::add_pointer<bool(const DataTypeDataLayoutISASelectorData &data)>::type |
Definition at line 111 of file CpuKernelSelectionTypes.h.
using DataTypeISASelectorPtr = std::add_pointer<bool(const DataTypeISASelectorData &data)>::type |
Definition at line 110 of file CpuKernelSelectionTypes.h.
using DepthwiseConv2dNativeDataTypeISASelectorPtr = std::add_pointer<bool(const DepthwiseConv2dNativeDataTypeISASelectorData &data)>::type |
Definition at line 115 of file CpuKernelSelectionTypes.h.
using ElementwiseDataTypeISASelectorPtr = std::add_pointer<bool(const ElementwiseDataTypeISASelectorData &data)>::type |
Definition at line 113 of file CpuKernelSelectionTypes.h.
using PoolDataTypeISASelectorPtr = std::add_pointer<bool(const PoolDataTypeISASelectorData &data)>::type |
Definition at line 112 of file CpuKernelSelectionTypes.h.
using ScaleKernelDataTypeISASelectorDataPtr = std::add_pointer<bool(const ScaleKernelDataTypeISASelectorData &data)>::type |
Definition at line 122 of file CpuKernelSelectionTypes.h.
using SoftmaxKernelDataTypeISASelectorDataPtr = std::add_pointer<bool(const SoftmaxKernelDataTypeISASelectorData &data)>::type |
Definition at line 124 of file CpuKernelSelectionTypes.h.
void arm_compute::cpu::kernels::convolve_nchw | ( | const Window & | window, |
const ITensor * | src, | ||
const ITensor * | weights, | ||
ITensor * | dst, | ||
const PadStrideInfo & | conv_info | ||
) |
Definition at line 47 of file impl.h.
References ARM_COMPUTE_UNUSED, arm_compute::calculate_max_window(), arm_compute::test::validation::conv_info, ITensorInfo::dimension(), Window::DimX, Window::DimY, Window::DimZ, arm_compute::test::validation::dst, arm_compute::execute_window_loop(), ITensor::info(), Iterator::ptr(), Window::set(), arm_compute::test::validation::src, ITensorInfo::strides_in_bytes(), type, arm_compute::wrapper::vdup_n(), arm_compute::wrapper::vloadq(), arm_compute::wrapper::vmla(), arm_compute::vreduce(), Dimensions< T >::x(), Dimensions< T >::y(), and Dimensions< T >::z().
void convolve_nhwc | ( | const Window & | window, |
const ITensor * | src, | ||
const ITensor * | weights, | ||
ITensor * | dst, | ||
const PadStrideInfo & | conv_info | ||
) |
Definition at line 58 of file impl.cpp.
References arm_compute::calculate_max_window(), arm_compute::test::validation::conv_info, ITensorInfo::dimension(), Window::DimX, Window::DimY, Window::DimZ, arm_compute::test::validation::dst, arm_compute::execute_window_loop(), ITensor::info(), Iterator::ptr(), Window::set(), arm_compute::test::validation::src, ITensorInfo::strides_in_bytes(), type, arm_compute::wrapper::vdup_n(), arm_compute::wrapper::vloadq(), arm_compute::wrapper::vmla(), arm_compute::vreduce(), Dimensions< T >::y(), and Dimensions< T >::z().
template void arm_compute::cpu::kernels::convolve_nhwc< float > | ( | const Window & | window, |
const ITensor * | src, | ||
const ITensor * | weights, | ||
ITensor * | dst, | ||
const PadStrideInfo & | conv_info | ||
) |
Referenced by neon_fp32_nhwc_directconv2d().
void arm_compute::cpu::kernels::internal_run_im2col_fp16_nchw_nopad | ( | const ITensor * | src, |
ITensor * | dst, | ||
const Window & | window, | ||
DataLayout | data_layout, | ||
const PadStrideInfo & | conv_info, | ||
std::pair< unsigned int, unsigned int > | convolved_dims, | ||
const Size2D & | kernel_dims, | ||
const Size2D & | dilation, | ||
uint32_t | input_pad_right, | ||
bool | has_bias | ||
) |
Definition at line 226 of file CpuIm2ColKernel.cpp.
References ARM_COMPUTE_UNUSED, arm_compute::test::validation::conv_info, arm_compute::cpu::data_layout, arm_compute::test::validation::dst, arm_compute::test::validation::has_bias, run_im2col_fp16_nchw_nopad(), and arm_compute::test::validation::src.
Referenced by CpuIm2ColKernel::configure().
void arm_compute::cpu::kernels::internal_run_im2col_fp16_nchw_pad | ( | const ITensor * | src, |
ITensor * | dst, | ||
const Window & | window, | ||
DataLayout | data_layout, | ||
const PadStrideInfo & | conv_info, | ||
std::pair< unsigned int, unsigned int > | convolved_dims, | ||
const Size2D & | kernel_dims, | ||
const Size2D & | dilation, | ||
uint32_t | input_pad_right, | ||
bool | has_bias | ||
) |
Definition at line 206 of file CpuIm2ColKernel.cpp.
References ARM_COMPUTE_UNUSED, arm_compute::test::validation::conv_info, arm_compute::cpu::data_layout, arm_compute::test::validation::dst, arm_compute::test::validation::has_bias, run_im2col_fp16_nchw_pad(), and arm_compute::test::validation::src.
Referenced by CpuIm2ColKernel::configure().
void arm_compute::cpu::kernels::internal_run_im2col_fp16_nopad | ( | const ITensor * | src, |
ITensor * | dst, | ||
const Window & | window, | ||
DataLayout | data_layout, | ||
const PadStrideInfo & | conv_info, | ||
std::pair< unsigned int, unsigned int > | convolved_dims, | ||
const Size2D & | kernel_dims, | ||
const Size2D & | dilation, | ||
uint32_t | input_pad_right, | ||
bool | has_bias | ||
) |
Definition at line 186 of file CpuIm2ColKernel.cpp.
References ARM_COMPUTE_UNUSED, arm_compute::test::validation::conv_info, arm_compute::cpu::data_layout, arm_compute::test::validation::dst, arm_compute::test::validation::has_bias, run_im2col_fp16_nopad(), and arm_compute::test::validation::src.
Referenced by CpuIm2ColKernel::configure().
void arm_compute::cpu::kernels::internal_run_im2col_fp16_pad | ( | const ITensor * | src, |
ITensor * | dst, | ||
const Window & | window, | ||
DataLayout | data_layout, | ||
const PadStrideInfo & | conv_info, | ||
std::pair< unsigned int, unsigned int > | convolved_dims, | ||
const Size2D & | kernel_dims, | ||
const Size2D & | dilation, | ||
uint32_t | input_pad_right, | ||
bool | has_bias | ||
) |
Definition at line 161 of file CpuIm2ColKernel.cpp.
References ARM_COMPUTE_UNUSED, arm_compute::test::validation::conv_info, arm_compute::cpu::data_layout, arm_compute::test::validation::dst, arm_compute::test::validation::has_bias, run_im2col_fp16_pad(), and arm_compute::test::validation::src.
Referenced by CpuIm2ColKernel::configure().
void arm_compute::cpu::kernels::linearize_volume_nchw | ( | const uint8_t *const | in_ptr, |
T * | out_ptr, | ||
bool | has_bias, | ||
int | top_left_x, | ||
int | top_left_y, | ||
int | kernel_width, | ||
int | kernel_height, | ||
int | kernel_depth, | ||
int | input_w, | ||
int | input_h, | ||
int | input_stride_x, | ||
int | input_stride_y, | ||
int | input_stride_z, | ||
int | pad_value, | ||
int | dilation_x, | ||
int | dilation_y | ||
) |
void arm_compute::cpu::kernels::linearize_volume_nhwc | ( | const uint8_t *const | in_ptr, |
T * | out_ptr, | ||
bool | has_bias, | ||
int | start_x, | ||
int | start_y, | ||
int | kernel_width, | ||
int | kernel_height, | ||
int | input_w, | ||
int | input_h, | ||
int | input_c, | ||
int | input_stride_y, | ||
int | input_stride_z, | ||
int | pad_value, | ||
int | dilation_x, | ||
int | dilation_y | ||
) |
Definition at line 149 of file impl.h.
References arm_compute::test::validation::has_bias.
void arm_compute::cpu::kernels::linearize_volume_nhwc | ( | const uint8_t *const | in_ptr, |
T * | out_ptr, | ||
bool | has_bias, | ||
int | start_x, | ||
int | start_y, | ||
int | kernel_width, | ||
int | kernel_height, | ||
int | input_w, | ||
int | input_h, | ||
int | input_c, | ||
int | input_stride_y, | ||
int | input_stride_z, | ||
int | pad_value, | ||
int | dilation_x, | ||
int | dilation_y, | ||
int | pad_right | ||
) |
Definition at line 223 of file impl.h.
References arm_compute::test::validation::has_bias.
void arm_compute::cpu::kernels::neon_fp16_nchw_directconv2d | ( | const Window & | window, |
const ITensor * | src, | ||
const ITensor * | weights, | ||
ITensor * | dst, | ||
const PadStrideInfo & | conv_info | ||
) |
void neon_fp32_nchw_directconv2d | ( | const Window & | window, |
const ITensor * | src, | ||
const ITensor * | weights, | ||
ITensor * | dst, | ||
const PadStrideInfo & | conv_info | ||
) |
Definition at line 48 of file all.cpp.
References arm_compute::test::validation::conv_info, arm_compute::test::validation::dst, and arm_compute::test::validation::src.
void neon_fp32_nhwc_directconv2d | ( | const Window & | window, |
const ITensor * | src, | ||
const ITensor * | weights, | ||
ITensor * | dst, | ||
const PadStrideInfo & | conv_info | ||
) |
Definition at line 33 of file fp32.cpp.
References arm_compute::test::validation::conv_info, convolve_nhwc< float >(), arm_compute::test::validation::dst, and arm_compute::test::validation::src.
void arm_compute::cpu::kernels::run_im2col | ( | const ITensor * | src, |
ITensor * | dst, | ||
const Window & | window, | ||
DataLayout | data_layout, | ||
const PadStrideInfo & | conv_info, | ||
std::pair< unsigned int, unsigned int > | convolved_dims, | ||
const Size2D & | kernel_dims, | ||
const Size2D & | dilation, | ||
uint32_t | input_pad_right, | ||
bool | has_bias | ||
) |
Definition at line 305 of file impl.h.
References arm_compute::CHANNEL, arm_compute::cpu::channel_idx, arm_compute::test::validation::conv_info, arm_compute::cpu::data_layout, Window::DimX, Window::DimY, Window::DimZ, arm_compute::test::validation::dst, arm_compute::execute_window_loop(), arm_compute::get_data_layout_dimension_index(), arm_compute::test::validation::has_bias, Size2D::height, arm_compute::HEIGHT, arm_compute::cpu::height_idx, arm_compute::is_data_type_quantized(), Iterator::ptr(), Window::set(), arm_compute::test::validation::src, Size2D::width, arm_compute::WIDTH, arm_compute::cpu::width_idx, Size2D::x(), and Size2D::y().
void arm_compute::cpu::kernels::run_im2col_bf16_nchw_nopad | ( | const ITensor * | src, |
ITensor * | dst, | ||
const Window & | window, | ||
DataLayout | data_layout, | ||
const PadStrideInfo & | conv_info, | ||
std::pair< unsigned int, unsigned int > | convolved_dims, | ||
const Size2D & | kernel_dims, | ||
const Size2D & | dilation, | ||
uint32_t | input_pad_right, | ||
bool | has_bias | ||
) |
Referenced by CpuIm2ColKernel::configure().
void arm_compute::cpu::kernels::run_im2col_bf16_nchw_pad | ( | const ITensor * | src, |
ITensor * | dst, | ||
const Window & | window, | ||
DataLayout | data_layout, | ||
const PadStrideInfo & | conv_info, | ||
std::pair< unsigned int, unsigned int > | convolved_dims, | ||
const Size2D & | kernel_dims, | ||
const Size2D & | dilation, | ||
uint32_t | input_pad_right, | ||
bool | has_bias | ||
) |
Referenced by CpuIm2ColKernel::configure().
void arm_compute::cpu::kernels::run_im2col_bf16_nopad | ( | const ITensor * | src, |
ITensor * | dst, | ||
const Window & | window, | ||
DataLayout | data_layout, | ||
const PadStrideInfo & | conv_info, | ||
std::pair< unsigned int, unsigned int > | convolved_dims, | ||
const Size2D & | kernel_dims, | ||
const Size2D & | dilation, | ||
uint32_t | input_pad_right, | ||
bool | has_bias | ||
) |
Referenced by CpuIm2ColKernel::configure().
void arm_compute::cpu::kernels::run_im2col_bf16_pad | ( | const ITensor * | src, |
ITensor * | dst, | ||
const Window & | window, | ||
DataLayout | data_layout, | ||
const PadStrideInfo & | conv_info, | ||
std::pair< unsigned int, unsigned int > | convolved_dims, | ||
const Size2D & | kernel_dims, | ||
const Size2D & | dilation, | ||
uint32_t | input_pad_right, | ||
bool | has_bias | ||
) |
Referenced by CpuIm2ColKernel::configure().
void run_im2col_fp16_nchw_nopad | ( | const ITensor * | src, |
ITensor * | dst, | ||
const Window & | window, | ||
DataLayout | data_layout, | ||
const PadStrideInfo & | conv_info, | ||
std::pair< unsigned int, unsigned int > | convolved_dims, | ||
const Size2D & | kernel_dims, | ||
const Size2D & | dilation, | ||
uint32_t | input_pad_right, | ||
bool | has_bias | ||
) |
Definition at line 62 of file fp16.cpp.
References ARM_COMPUTE_UNUSED, arm_compute::test::validation::conv_info, arm_compute::cpu::data_layout, arm_compute::test::validation::dst, arm_compute::test::validation::has_bias, and arm_compute::test::validation::src.
Referenced by internal_run_im2col_fp16_nchw_nopad().
void run_im2col_fp16_nchw_pad | ( | const ITensor * | src, |
ITensor * | dst, | ||
const Window & | window, | ||
DataLayout | data_layout, | ||
const PadStrideInfo & | conv_info, | ||
std::pair< unsigned int, unsigned int > | convolved_dims, | ||
const Size2D & | kernel_dims, | ||
const Size2D & | dilation, | ||
uint32_t | input_pad_right, | ||
bool | has_bias | ||
) |
Definition at line 42 of file fp16.cpp.
References ARM_COMPUTE_UNUSED, arm_compute::test::validation::conv_info, arm_compute::cpu::data_layout, arm_compute::test::validation::dst, arm_compute::test::validation::has_bias, and arm_compute::test::validation::src.
Referenced by internal_run_im2col_fp16_nchw_pad().
void run_im2col_fp16_nopad | ( | const ITensor * | src, |
ITensor * | dst, | ||
const Window & | window, | ||
DataLayout | data_layout, | ||
const PadStrideInfo & | conv_info, | ||
std::pair< unsigned int, unsigned int > | convolved_dims, | ||
const Size2D & | kernel_dims, | ||
const Size2D & | dilation, | ||
uint32_t | input_pad_right, | ||
bool | has_bias | ||
) |
Definition at line 54 of file fp16.cpp.
References ARM_COMPUTE_UNUSED, arm_compute::test::validation::conv_info, arm_compute::cpu::data_layout, arm_compute::test::validation::dst, arm_compute::test::validation::has_bias, and arm_compute::test::validation::src.
Referenced by internal_run_im2col_fp16_nopad().
void run_im2col_fp16_pad | ( | const ITensor * | src, |
ITensor * | dst, | ||
const Window & | window, | ||
DataLayout | data_layout, | ||
const PadStrideInfo & | conv_info, | ||
std::pair< unsigned int, unsigned int > | convolved_dims, | ||
const Size2D & | kernel_dims, | ||
const Size2D & | dilation, | ||
uint32_t | input_pad_right, | ||
bool | has_bias | ||
) |
Definition at line 34 of file fp16.cpp.
References ARM_COMPUTE_UNUSED, arm_compute::test::validation::conv_info, arm_compute::cpu::data_layout, arm_compute::test::validation::dst, arm_compute::test::validation::has_bias, and arm_compute::test::validation::src.
Referenced by internal_run_im2col_fp16_pad().
void run_im2col_fp32_nchw_nopad | ( | const ITensor * | src, |
ITensor * | dst, | ||
const Window & | window, | ||
DataLayout | data_layout, | ||
const PadStrideInfo & | conv_info, | ||
std::pair< unsigned int, unsigned int > | convolved_dims, | ||
const Size2D & | kernel_dims, | ||
const Size2D & | dilation, | ||
uint32_t | input_pad_right, | ||
bool | has_bias | ||
) |
Definition at line 69 of file all.cpp.
References arm_compute::test::validation::conv_info, arm_compute::cpu::data_layout, arm_compute::test::validation::dst, arm_compute::test::validation::has_bias, and arm_compute::test::validation::src.
Referenced by CpuIm2ColKernel::configure().
void run_im2col_fp32_nchw_pad | ( | const ITensor * | src, |
ITensor * | dst, | ||
const Window & | window, | ||
DataLayout | data_layout, | ||
const PadStrideInfo & | conv_info, | ||
std::pair< unsigned int, unsigned int > | convolved_dims, | ||
const Size2D & | kernel_dims, | ||
const Size2D & | dilation, | ||
uint32_t | input_pad_right, | ||
bool | has_bias | ||
) |
Definition at line 54 of file all.cpp.
References arm_compute::test::validation::conv_info, arm_compute::cpu::data_layout, arm_compute::test::validation::dst, arm_compute::test::validation::has_bias, and arm_compute::test::validation::src.
Referenced by CpuIm2ColKernel::configure().
void run_im2col_fp32_nopad | ( | const ITensor * | src, |
ITensor * | dst, | ||
const Window & | window, | ||
DataLayout | data_layout, | ||
const PadStrideInfo & | conv_info, | ||
std::pair< unsigned int, unsigned int > | convolved_dims, | ||
const Size2D & | kernel_dims, | ||
const Size2D & | dilation, | ||
uint32_t | input_pad_right, | ||
bool | has_bias | ||
) |
Definition at line 69 of file CpuIm2ColKernel.cpp.
References arm_compute::test::validation::conv_info, arm_compute::cpu::data_layout, arm_compute::test::validation::dst, arm_compute::test::validation::has_bias, and arm_compute::test::validation::src.
Referenced by CpuIm2ColKernel::configure().
void run_im2col_fp32_pad | ( | const ITensor * | src, |
ITensor * | dst, | ||
const Window & | window, | ||
DataLayout | data_layout, | ||
const PadStrideInfo & | conv_info, | ||
std::pair< unsigned int, unsigned int > | convolved_dims, | ||
const Size2D & | kernel_dims, | ||
const Size2D & | dilation, | ||
uint32_t | input_pad_right, | ||
bool | has_bias | ||
) |
Definition at line 54 of file CpuIm2ColKernel.cpp.
References arm_compute::test::validation::conv_info, arm_compute::cpu::data_layout, arm_compute::test::validation::dst, arm_compute::test::validation::has_bias, and arm_compute::test::validation::src.
Referenced by CpuIm2ColKernel::configure().
void arm_compute::cpu::kernels::run_im2col_int8_nopad_nhwc | ( | const ITensor * | src, |
ITensor * | dst, | ||
const Window & | window, | ||
DataLayout | data_layout, | ||
const PadStrideInfo & | conv_info, | ||
std::pair< unsigned int, unsigned int > | convolved_dims, | ||
const Size2D & | kernel_dims, | ||
const Size2D & | dilation, | ||
uint32_t | input_pad_right, | ||
bool | has_bias | ||
) |
Definition at line 116 of file CpuIm2ColKernel.cpp.
References arm_compute::test::validation::conv_info, arm_compute::cpu::data_layout, arm_compute::test::validation::dst, arm_compute::test::validation::has_bias, and arm_compute::test::validation::src.
Referenced by CpuIm2ColKernel::configure().
void run_im2col_qasymm8_nchw_nopad | ( | const ITensor * | src, |
ITensor * | dst, | ||
const Window & | window, | ||
DataLayout | data_layout, | ||
const PadStrideInfo & | conv_info, | ||
std::pair< unsigned int, unsigned int > | convolved_dims, | ||
const Size2D & | kernel_dims, | ||
const Size2D & | dilation, | ||
uint32_t | input_pad_right, | ||
bool | has_bias | ||
) |
Definition at line 99 of file all.cpp.
References arm_compute::test::validation::conv_info, arm_compute::cpu::data_layout, arm_compute::test::validation::dst, arm_compute::test::validation::has_bias, and arm_compute::test::validation::src.
Referenced by CpuIm2ColKernel::configure().
void run_im2col_qasymm8_nchw_pad | ( | const ITensor * | src, |
ITensor * | dst, | ||
const Window & | window, | ||
DataLayout | data_layout, | ||
const PadStrideInfo & | conv_info, | ||
std::pair< unsigned int, unsigned int > | convolved_dims, | ||
const Size2D & | kernel_dims, | ||
const Size2D & | dilation, | ||
uint32_t | input_pad_right, | ||
bool | has_bias | ||
) |
Definition at line 84 of file all.cpp.
References arm_compute::test::validation::conv_info, arm_compute::cpu::data_layout, arm_compute::test::validation::dst, arm_compute::test::validation::has_bias, and arm_compute::test::validation::src.
Referenced by CpuIm2ColKernel::configure().
void arm_compute::cpu::kernels::run_im2col_qasymm8_nopad | ( | const ITensor * | src, |
ITensor * | dst, | ||
const Window & | window, | ||
DataLayout | data_layout, | ||
const PadStrideInfo & | conv_info, | ||
std::pair< unsigned int, unsigned int > | convolved_dims, | ||
const Size2D & | kernel_dims, | ||
const Size2D & | dilation, | ||
uint32_t | input_pad_right, | ||
bool | has_bias | ||
) |
Definition at line 49 of file qasymm8.cpp.
References arm_compute::test::validation::conv_info, arm_compute::cpu::data_layout, arm_compute::test::validation::dst, arm_compute::test::validation::has_bias, and arm_compute::test::validation::src.
void arm_compute::cpu::kernels::run_im2col_qasymm8_pad | ( | const ITensor * | src, |
ITensor * | dst, | ||
const Window & | window, | ||
DataLayout | data_layout, | ||
const PadStrideInfo & | conv_info, | ||
std::pair< unsigned int, unsigned int > | convolved_dims, | ||
const Size2D & | kernel_dims, | ||
const Size2D & | dilation, | ||
uint32_t | input_pad_right, | ||
bool | has_bias | ||
) |
Definition at line 34 of file qasymm8.cpp.
References arm_compute::test::validation::conv_info, arm_compute::cpu::data_layout, arm_compute::test::validation::dst, arm_compute::test::validation::has_bias, and arm_compute::test::validation::src.
void arm_compute::cpu::kernels::run_im2col_qasymm8_pad_nhwc | ( | const ITensor * | src, |
ITensor * | dst, | ||
const Window & | window, | ||
DataLayout | data_layout, | ||
const PadStrideInfo & | conv_info, | ||
std::pair< unsigned int, unsigned int > | convolved_dims, | ||
const Size2D & | kernel_dims, | ||
const Size2D & | dilation, | ||
uint32_t | input_pad_right, | ||
bool | has_bias | ||
) |
Definition at line 146 of file CpuIm2ColKernel.cpp.
References arm_compute::test::validation::conv_info, arm_compute::cpu::data_layout, arm_compute::test::validation::dst, arm_compute::test::validation::has_bias, and arm_compute::test::validation::src.
Referenced by CpuIm2ColKernel::configure().
void arm_compute::cpu::kernels::run_im2col_uint8_nopad_nhwc | ( | const ITensor * | src, |
ITensor * | dst, | ||
const Window & | window, | ||
DataLayout | data_layout, | ||
const PadStrideInfo & | conv_info, | ||
std::pair< unsigned int, unsigned int > | convolved_dims, | ||
const Size2D & | kernel_dims, | ||
const Size2D & | dilation, | ||
uint32_t | input_pad_right, | ||
bool | has_bias | ||
) |
Definition at line 131 of file CpuIm2ColKernel.cpp.
References arm_compute::test::validation::conv_info, arm_compute::cpu::data_layout, arm_compute::test::validation::dst, arm_compute::test::validation::has_bias, and arm_compute::test::validation::src.
Referenced by CpuIm2ColKernel::configure().
std::pair<Status, Window> arm_compute::cpu::kernels::validate_and_configure_window | ( | ITensorInfo * | src, |
ITensorInfo * | dst | ||
) |
Definition at line 92 of file CpuDirectConv2dKernel.cpp.
References ARM_COMPUTE_CREATE_ERROR, ARM_COMPUTE_ERROR_ON, ARM_COMPUTE_UNUSED, arm_compute::calculate_max_window(), arm_compute::test::validation::dst, arm_compute::RUNTIME_ERROR, arm_compute::test::validation::src, and arm_compute::UNKNOWN.
Referenced by CpuConvertQuantizedSignednessKernel::configure(), CpuCopyKernel::configure(), CpuPool2dKernel::configure(), ClGemmLowpMatrixMultiplyNativeKernel::configure(), NEInstanceNormalizationLayerKernel::configure(), CpuDirectConv2dKernel::configure(), NEFFTScaleKernel::configure(), ClGemmMatrixMultiplyNativeKernel::configure(), NEFFTDigitReverseKernel::configure(), CLChannelShuffleLayerKernel::configure(), ClGemmMatrixMultiplyReshapedOnlyRhsMMULKernel::configure(), ClWinogradFilterTransformKernel::configure(), ClWinogradInputTransformKernel::configure(), ClWinogradOutputTransformKernel::configure(), CLQLSTMLayerNormalizationKernel::configure(), CLNormalizationLayerKernel::configure(), NEMeanStdDevNormalizationKernel::configure(), CLGatherKernel::configure(), NEFFTRadixStageKernel::configure(), ClGemmLowpMatrixMultiplyReshapedKernel::configure(), CLComparisonKernel::configure(), CLFFTDigitReverseKernel::configure(), ClGemmReshapeRhsMatrixKernel::configure(), ClCol2ImKernel::configure(), CLFFTRadixStageKernel::configure(), NEStridedSliceKernel::configure(), ClGemmLowpMatrixMultiplyReshapedOnlyRhsKernel::configure(), ClGemmMatrixMultiplyReshapedOnlyRhsKernel::configure(), CLPriorBoxLayerKernel::configure(), CLStackLayerKernel::configure(), ClIm2ColKernel::configure(), ClGemmMatrixMultiplyReshapedKernel::configure(), CLDeconvolutionReshapeOutputKernel::configure(), CpuCopyKernel::validate(), CpuActivationKernel::validate(), CpuPool2dKernel::validate(), CpuDirectConv2dKernel::validate(), NEFFTScaleKernel::validate(), ClGemmLowpMatrixMultiplyNativeKernel::validate(), NEInstanceNormalizationLayerKernel::validate(), ClWinogradFilterTransformKernel::validate(), ClWinogradInputTransformKernel::validate(), NEFFTDigitReverseKernel::validate(), CLChannelShuffleLayerKernel::validate(), NEFFTRadixStageKernel::validate(), NEMeanStdDevNormalizationKernel::validate(), ClWinogradOutputTransformKernel::validate(), ClGemmMatrixMultiplyNativeKernel::validate(), ClGemmReshapeRhsMatrixKernel::validate(), ClGemmMatrixMultiplyReshapedOnlyRhsMMULKernel::validate(), CLNormalizationLayerKernel::validate(), CLQLSTMLayerNormalizationKernel::validate(), ClGemmLowpMatrixMultiplyReshapedKernel::validate(), CLComparisonKernel::validate(), CLGatherKernel::validate(), CLFFTDigitReverseKernel::validate(), ClCol2ImKernel::validate(), CLFFTRadixStageKernel::validate(), ClGemmLowpMatrixMultiplyReshapedOnlyRhsMMULKernel::validate(), ClGemmLowpMatrixMultiplyReshapedOnlyRhsKernel::validate(), NEStridedSliceKernel::validate(), CLPriorBoxLayerKernel::validate(), ClIm2ColKernel::validate(), and CLStackLayerKernel::validate().
Status arm_compute::cpu::kernels::validate_arguments | ( | const ITensorInfo * | src, |
const ITensorInfo * | weights, | ||
const ITensorInfo * | dst, | ||
const PadStrideInfo & | conv_info | ||
) |
Definition at line 57 of file CpuDirectConv2dKernel.cpp.
References ARM_COMPUTE_RETURN_ERROR_ON, ARM_COMPUTE_RETURN_ERROR_ON_CPU_F16_UNSUPPORTED, ARM_COMPUTE_RETURN_ERROR_ON_DATA_TYPE_CHANNEL_NOT_IN, ARM_COMPUTE_RETURN_ERROR_ON_MISMATCHING_DATA_TYPES, ARM_COMPUTE_RETURN_ERROR_ON_MISMATCHING_DIMENSIONS, ARM_COMPUTE_RETURN_ERROR_ON_NULLPTR, ARM_COMPUTE_UNUSED, arm_compute::CHANNEL, arm_compute::cpu::channel_idx, arm_compute::misc::shape_calculator::compute_deep_convolution_shape(), arm_compute::test::validation::conv_info, arm_compute::cpu::data_layout, arm_compute::test::validation::data_type, ITensorInfo::dimension(), arm_compute::test::validation::dst, arm_compute::F16, arm_compute::F32, arm_compute::get_data_layout_dimension_index(), arm_compute::HEIGHT, arm_compute::cpu::height_idx, arm_compute::NHWC, ITensorInfo::num_dimensions(), arm_compute::test::validation::output_shape, arm_compute::test::validation::src, arm_compute::UNKNOWN, arm_compute::WIDTH, and arm_compute::cpu::width_idx.
Referenced by CpuConvertQuantizedSignednessKernel::configure(), CpuDequantizeKernel::configure(), CpuReshapeKernel::configure(), CpuCopyKernel::configure(), ClReshapeKernel::configure(), ClDequantizeKernel::configure(), ClFloorKernel::configure(), CpuConcatenateBatchKernel::configure(), CpuFloorKernel::configure(), CpuPermuteKernel::configure(), ClCopyKernel::configure(), ClElementWiseUnaryKernel::configure(), CpuConcatenateWidthKernel::configure(), CpuConcatenateHeightKernel::configure(), ClWidthConcatenate2TensorsKernel::configure(), CpuQuantizeKernel::configure(), ClPool3dKernel::configure(), ClPool2dKernel::configure(), ClHeightConcatenateKernel::configure(), ClQuantizeKernel::configure(), ClScaleKernel::configure(), ClWidthConcatenateKernel::configure(), CPPDetectionOutputLayer::configure(), ClPermuteKernel::configure(), ClWidthConcatenate4TensorsKernel::configure(), ClActivationKernel::configure(), CLStridedSliceKernel::configure(), ClBatchConcatenateKernel::configure(), ClDepthConcatenateKernel::configure(), CpuActivationKernel::configure(), CpuConcatenateDepthKernel::configure(), CpuPool2dKernel::configure(), NETileKernel::configure(), ClGemmLowpMatrixMultiplyNativeKernel::configure(), NEChannelShuffleLayerKernel::configure(), CpuDirectConv2dOutputStageKernel::configure(), NEDepthToSpaceLayerKernel::configure(), NEPriorBoxLayerKernel::configure(), NEReverseKernel::configure(), ClGemmReshapeLhsMatrixKernel::configure(), CpuDirectConv2dKernel::configure(), CPPTopKVKernel::configure(), CpuGemmLowpMatrixMultiplyKernel::configure(), CpuMaxUnpoolingLayerKernel::configure(), NEComputeAllAnchorsKernel::configure(), NEInstanceNormalizationLayerKernel::configure(), NEReorgLayerKernel::configure(), NESpaceToDepthLayerKernel::configure(), CLInstanceNormalizationLayerKernel::configure(), CLMaxUnpoolingLayerKernel::configure(), NEFFTScaleKernel::configure(), ClGemmMatrixMultiplyNativeKernel::configure(), ClIndirectConv2dAddressPrecalculationKernel::configure(), ClWinogradFilterTransformKernel::configure(), ClWinogradInputTransformKernel::configure(), CPPPermuteKernel::configure(), NEBatchToSpaceLayerKernel::configure(), NEFFTDigitReverseKernel::configure(), CpuPool3dKernel::configure(), CLChannelShuffleLayerKernel::configure(), NESpaceToBatchLayerKernel::configure(), ClGemmLowpQuantizeDownInt32ScaleByFixedPointKernel::configure(), ClGemmMatrixMultiplyReshapedOnlyRhsMMULKernel::configure(), ClIndirectConv2dKernel::configure(), NENormalizationLayerKernel::configure(), CLSelectKernel::configure(), ClWinogradOutputTransformKernel::configure(), CpuSubKernel::configure(), CLComputeAllAnchorsKernel::configure(), ClGemmLowpQuantizeDownInt32ScaleByFloatKernel::configure(), ClGemmLowpQuantizeDownInt32ScaleKernel::configure(), CLFFTScaleKernel::configure(), CLNormalizationLayerKernel::configure(), CpuGemmLowpOffsetContributionKernel::configure(), CLQLSTMLayerNormalizationKernel::configure(), NEPadLayerKernel::configure(), NERangeKernel::configure(), CLDepthToSpaceLayerKernel::configure(), CLSpaceToDepthLayerKernel::configure(), CLTileKernel::configure(), CPPNonMaximumSuppressionKernel::configure(), CPPDetectionPostProcessLayer::configure(), NEBoundingBoxTransformKernel::configure(), NEFFTRadixStageKernel::configure(), CLGatherKernel::configure(), NEROIPoolingLayerKernel::configure(), CLSpaceToBatchLayerKernel::configure(), CpuAddMulAddKernel::configure(), CpuDirectConv3dKernel::configure(), CpuGemmLowpQuantizeDownInt32ScaleKernel::configure(), CLComparisonKernel::configure(), ClCastKernel::configure(), NEReductionOperationKernel::configure(), ClGemmLowpMatrixMultiplyReshapedKernel::configure(), NEStackLayerKernel::configure(), CLFFTDigitReverseKernel::configure(), CpuCol2ImKernel::configure(), CpuDepthwiseConv2dNativeKernel::configure(), CLBatchToSpaceLayerKernel::configure(), NEFuseBatchNormalizationKernel::configure(), CLReorgLayerKernel::configure(), ClGemmLowpMatrixMultiplyReshapedOnlyRhsMMULKernel::configure(), ClGemmLowpOffsetContributionKernel::configure(), ClGemmLowpOffsetContributionOutputStageKernel::configure(), ClGemmReshapeRhsMatrixKernel::configure(), CpuCastKernel::configure(), CLNormalizePlanarYUVLayerKernel::configure(), CpuGemmLowpQuantizeDownInt32ToInt16ScaleByFixedPointKernel::configure(), NEROIAlignLayerKernel::configure(), CpuAddKernel::configure(), CpuGemmMatrixMultiplyKernel::configure(), NEGatherKernel::configure(), CpuScaleKernel::configure(), CLRangeKernel::configure(), CLReductionOperationKernel::configure(), CLReverseKernel::configure(), NEBatchNormalizationLayerKernel::configure(), CLFFTRadixStageKernel::configure(), CpuGemmLowpQuantizeDownInt32ToInt8ScaleByFixedPointKernel::configure(), CpuGemmLowpQuantizeDownInt32ToUint8ScaleByFixedPointKernel::configure(), CpuMulKernel::configure(), ClCol2ImKernel::configure(), ClDirectConv2dKernel::configure(), NEStridedSliceKernel::configure(), ClDirectConv3dKernel::configure(), CLL2NormalizeLayerKernel::configure(), ClGemmLowpMatrixMultiplyReshapedOnlyRhsKernel::configure(), CLPadLayerKernel::configure(), CpuWeightsReshapeKernel::configure(), ClMulKernel::configure(), CLArgMinMaxLayerKernel::configure(), CLDepthwiseConvolutionLayerNativeKernel::configure(), CLBoundingBoxTransformKernel::configure(), ClGemmMatrixMultiplyReshapedOnlyRhsKernel::configure(), ClWeightsReshapeKernel::configure(), CLPriorBoxLayerKernel::configure(), CLStackLayerKernel::configure(), ClIm2ColKernel::configure(), CLROIAlignLayerKernel::configure(), CpuIm2ColKernel::configure(), ClGemmMatrixMultiplyReshapedKernel::configure(), CLDeconvolutionReshapeOutputKernel::configure(), CpuGemmLowpOffsetContributionOutputStageKernel::configure(), CLFuseBatchNormalizationKernel::configure(), CLBatchNormalizationLayerKernel::configure(), ClWinogradConv2d::configure(), CpuFloorKernel::infer_window(), CpuConvertQuantizedSignednessKernel::validate(), CpuDequantizeKernel::validate(), CpuCopyKernel::validate(), CpuReshapeKernel::validate(), ClReshapeKernel::validate(), ClDequantizeKernel::validate(), ClFloorKernel::validate(), CpuFloorKernel::validate(), CpuPermuteKernel::validate(), CpuConcatenateBatchKernel::validate(), CpuConcatenateHeightKernel::validate(), CpuConcatenateWidthKernel::validate(), ClWidthConcatenate2TensorsKernel::validate(), CpuQuantizeKernel::validate(), ClTransposedConvolutionKernel::validate(), ClCopyKernel::validate(), ClElementWiseUnaryKernel::validate(), ClQuantizeKernel::validate(), ClWidthConcatenateKernel::validate(), ClScaleKernel::validate(), ClHeightConcatenateKernel::validate(), ClPool3dKernel::validate(), ClPool2dKernel::validate(), ClBatchConcatenateKernel::validate(), ClDepthConcatenateKernel::validate(), ClPermuteKernel::validate(), CpuActivationKernel::validate(), CpuPool2dKernel::validate(), CpuConcatenateDepthKernel::validate(), ClActivationKernel::validate(), ClWidthConcatenate4TensorsKernel::validate(), NETileKernel::validate(), CpuDirectConv2dKernel::validate(), CpuGemmLowpMatrixMultiplyKernel::validate(), CPPDetectionOutputLayer::validate(), NEChannelShuffleLayerKernel::validate(), NEDepthToSpaceLayerKernel::validate(), NESpaceToDepthLayerKernel::validate(), CpuPool3dKernel::validate(), NEPriorBoxLayerKernel::validate(), CpuDirectConv2dOutputStageKernel::validate(), NEFFTScaleKernel::validate(), ClGemmReshapeLhsMatrixKernel::validate(), CpuMaxUnpoolingLayerKernel::validate(), NEComputeAllAnchorsKernel::validate(), NEReorgLayerKernel::validate(), CPPPermuteKernel::validate(), NEInstanceNormalizationLayerKernel::validate(), ClGemmLowpMatrixMultiplyNativeKernel::validate(), NEReverseKernel::validate(), ClWinogradInputTransformKernel::validate(), CPPTopKVKernel::validate(), CpuSubKernel::validate(), ClWinogradFilterTransformKernel::validate(), NEFFTDigitReverseKernel::validate(), ClGemmLowpQuantizeDownInt32ScaleByFixedPointKernel::validate(), ClIndirectConv2dAddressPrecalculationKernel::validate(), CLDepthToSpaceLayerKernel::validate(), CLSpaceToDepthLayerKernel::validate(), CpuGemmLowpQuantizeDownInt32ScaleKernel::validate(), CLChannelShuffleLayerKernel::validate(), ClCastKernel::validate(), CpuCol2ImKernel::validate(), NEMeanStdDevNormalizationKernel::validate(), NERangeKernel::validate(), ClGemmLowpQuantizeDownInt32ScaleKernel::validate(), ClGemmLowpQuantizeDownInt32ScaleByFloatKernel::validate(), NEFFTRadixStageKernel::validate(), NENormalizationLayerKernel::validate(), CpuCastKernel::validate(), ClWinogradOutputTransformKernel::validate(), CLInstanceNormalizationLayerKernel::validate(), CLComputeAllAnchorsKernel::validate(), CpuGemmLowpOffsetContributionKernel::validate(), CLSelectKernel::validate(), CLFFTScaleKernel::validate(), ClGemmMatrixMultiplyNativeKernel::validate(), CpuAddKernel::validate(), ClGemmMatrixMultiplyReshapedOnlyRhsMMULKernel::validate(), CpuDirectConv3dKernel::validate(), CLMaxUnpoolingLayerKernel::validate(), NEGatherKernel::validate(), ClGemmReshapeRhsMatrixKernel::validate(), ClIndirectConv2dKernel::validate(), NEStackLayerKernel::validate(), CLNormalizationLayerKernel::validate(), CpuDepthwiseConv2dNativeKernel::validate(), ClGemmLowpMatrixMultiplyReshapedKernel::validate(), CLRangeKernel::validate(), CLQLSTMLayerNormalizationKernel::validate(), CLReorgLayerKernel::validate(), NEBoundingBoxTransformKernel::validate(), CLStridedSliceKernel::validate(), CLTileKernel::validate(), NEReductionOperationKernel::validate(), CLComparisonKernel::validate(), CpuWeightsReshapeKernel::validate(), CLMeanStdDevNormalizationKernel::validate(), CpuAddMulAddKernel::validate(), CLFFTDigitReverseKernel::validate(), ClGemmLowpOffsetContributionKernel::validate(), NEPadLayerKernel::validate(), CpuScaleKernel::validate(), CLGatherKernel::validate(), CpuGemmMatrixMultiplyKernel::validate(), CPPNonMaximumSuppressionKernel::validate(), CpuGemmLowpQuantizeDownInt32ToInt16ScaleByFixedPointKernel::validate(), CLFFTRadixStageKernel::validate(), ClCol2ImKernel::validate(), CpuMulKernel::validate(), ClGemmLowpMatrixMultiplyReshapedOnlyRhsMMULKernel::validate(), ClDirectConv3dKernel::validate(), ClDirectConv2dKernel::validate(), NEROIPoolingLayerKernel::validate(), NEROIAlignLayerKernel::validate(), CLNormalizePlanarYUVLayerKernel::validate(), ClGemmLowpOffsetContributionOutputStageKernel::validate(), NEBatchToSpaceLayerKernel::validate(), CpuGemmLowpQuantizeDownInt32ToUint8ScaleByFixedPointKernel::validate(), CpuGemmLowpQuantizeDownInt32ToInt8ScaleByFixedPointKernel::validate(), CLReverseKernel::validate(), CLReductionOperationKernel::validate(), CPPDetectionPostProcessLayer::validate(), NESpaceToBatchLayerKernel::validate(), CpuWinogradConv2d::validate(), ClGemmLowpMatrixMultiplyReshapedOnlyRhsKernel::validate(), ClMulKernel::validate(), ClWeightsReshapeKernel::validate(), CLPadLayerKernel::validate(), ClGemmMatrixMultiplyReshapedOnlyRhsKernel::validate(), CLArgMinMaxLayerKernel::validate(), CLL2NormalizeLayerKernel::validate(), NEBatchNormalizationLayerKernel::validate(), CLBoundingBoxTransformKernel::validate(), NEStridedSliceKernel::validate(), CLPriorBoxLayerKernel::validate(), ClIm2ColKernel::validate(), NEFuseBatchNormalizationKernel::validate(), CpuIm2ColKernel::validate(), CLStackLayerKernel::validate(), CLROIAlignLayerKernel::validate(), ClGemmMatrixMultiplyReshapedKernel::validate(), CpuGemmLowpOffsetContributionOutputStageKernel::validate(), CLDepthwiseConvolutionLayerNativeKernel::validate(), CLDeconvolutionReshapeOutputKernel::validate(), CLBatchToSpaceLayerKernel::validate(), ClWinogradConv2d::validate(), CLSpaceToBatchLayerKernel::validate(), CLBatchNormalizationLayerKernel::validate(), and CLFuseBatchNormalizationKernel::validate().