|
24.04
|
|
24.04
|
Copyright (c) 2017-2024 Arm Limited. More...
Namespaces | |
| assembly_utils | |
| cl_direct_conv | |
| cl_dwc | |
| cl_gemm | |
| cl_indirect_conv | |
| cl_matmul | |
| cl_tuner | |
| cpu | |
| cpuinfo | |
| detail | |
| experimental | |
| gpu | |
| graph | |
| graph_utils | |
| helpers | |
| io | |
| kernels | |
| logging | |
| misc | |
| mlgo | |
| opencl | |
| Interface to convert the 2D Fully Connected weights from NCHW to NHWC or vice versa. | |
| quantization | |
| scale_helpers | |
| scale_utils | |
| scheduler_utils | |
| softmax_helpers | |
| support | |
| test | |
| utility | |
| utils | |
| weights_transformations | |
| wrapper | |
Data Structures | |
| class | AccessWindowAutoPadding |
| Dummy access window. More... | |
| class | AccessWindowHorizontal |
| Implementation of a row access pattern. More... | |
| class | AccessWindowRectangle |
| Implementation of a rectangular access pattern. More... | |
| class | AccessWindowStatic |
| Implementation of a static rectangular access pattern. More... | |
| class | AccessWindowTranspose |
| Implementation of a XY-transpose access pattern. More... | |
| class | AccessWindowVertical |
| Implementation of a column access pattern. More... | |
| class | ActivationLayerInfo |
| Activation Layer Information class. More... | |
| class | Allocator |
| Default malloc allocator implementation. More... | |
| class | AllocatorWrapper |
| Default malloc allocator implementation. More... | |
| class | Array |
| Basic implementation of the IArray interface which allocates a static number of T values More... | |
| class | bfloat16 |
| Brain floating point representation class. More... | |
| struct | BlobInfo |
| Meta-data information for each blob. More... | |
| class | BlobLifetimeManager |
| Concrete class that tracks the lifetime of registered tensors and calculates the systems memory requirements in terms of blobs. More... | |
| class | BlobMemoryPool |
| Blob memory pool. More... | |
| struct | BorderSize |
| Container for 2D border size. More... | |
| class | BoundingBoxTransformInfo |
| Bounding Box Transform information class. More... | |
| class | BoxNMSLimitInfo |
| BoxWithNonMaximaSuppressionLimit Information class. More... | |
| class | CLAbsLayer |
| Basic function to get the absolute value of an input tensor. More... | |
| class | CLActivationLayer |
| Basic function to run opencl::kernels::ClActivationKernel. More... | |
| class | CLArgMinMaxLayer |
| Function to calculate the index of the minimum or maximum values in a tensor based on an axis. More... | |
| class | CLArgMinMaxLayerKernel |
| Interface for the reduction operation kernel. More... | |
| class | CLArithmeticAddition |
| Basic function to run opencl::kernels::ClSaturatedArithmeticKernel for addition. More... | |
| class | CLArithmeticDivision |
| Basic function to run opencl::kernels::ClSaturatedArithmeticKernel for division. More... | |
| class | CLArithmeticSubtraction |
| Basic function to run opencl::kernels::ClSaturatedArithmeticKernel for subtraction. More... | |
| class | CLArray |
| CLArray implementation More... | |
| class | CLBatchNormalizationLayer |
| Basic function to run CLNormalizationLayerKernel and simulate a batch normalization layer. More... | |
| class | CLBatchNormalizationLayerKernel |
| Interface for the BatchNormalization layer kernel. More... | |
| class | CLBatchToSpaceLayer |
| Basic function to run CLBatchToSpaceLayerKernel. More... | |
| class | CLBatchToSpaceLayerKernel |
| Interface for the batch to space kernel. More... | |
| class | CLBitwiseAnd |
| Basic function to perform bitwise AND by running CLBitwiseKernel. More... | |
| class | CLBitwiseKernel |
| Interface for the bitwise operation kernel. More... | |
| class | CLBitwiseNot |
| Basic function to perform bitwise NOT by running CLBitwiseKernel. More... | |
| class | CLBitwiseOr |
| Basic function to perform bitwise OR by running CLBitwiseKernel. More... | |
| class | CLBitwiseXor |
| Basic function to perform bitwise XOR by running CLBitwiseKernel. More... | |
| class | CLBoundingBoxTransform |
| Basic function to run CLBoundingBoxTransformKernel. More... | |
| class | CLBoundingBoxTransformKernel |
| Interface for the bounding box kernel. More... | |
| class | CLBufferAllocator |
| Default OpenCL cl buffer allocator implementation. More... | |
| class | CLBufferMemoryRegion |
| OpenCL buffer memory region implementation. More... | |
| class | CLBuildOptions |
| Build options. More... | |
| class | CLCast |
| Basic function to run opencl::kernels::ClCastKernel. More... | |
| class | CLChannelShuffleLayer |
| Basic function to run CLChannelShuffleLayerKernel. More... | |
| class | CLChannelShuffleLayerKernel |
| Interface for the channel shuffle kernel. More... | |
| class | CLCoarseSVMMemoryRegion |
| OpenCL coarse-grain SVM memory region implementation. More... | |
| class | CLCommandBuffer |
| Command buffer contains a list of commands that is constructed once and later enqueued multiple times. More... | |
| class | CLComparison |
| Basic function to run CLComparisonKernel. More... | |
| class | CLComparisonKernel |
| Interface for the comparison kernel. More... | |
| class | CLComparisonStatic |
| Basic function to run CLComparisonKernel. More... | |
| class | CLCompatCommandBuffer |
| Command buffer implementation for platform without mutable dispatch command buffer extension. More... | |
| class | CLCompileContext |
| CLCompileContext class. More... | |
| class | CLComplexPixelWiseMultiplication |
| Basic function to run opencl::ClComplexMul. More... | |
| class | CLComputeAllAnchorsKernel |
| Interface for Compute All Anchors kernel. More... | |
| class | CLComputeMeanVariance |
| Interface for compute Mean and Variance per channel. More... | |
| class | CLConcatenateLayer |
| Basic function to execute concatenate tensors along a given axis. More... | |
| class | CLConv3D |
| Basic function to compute the convolution3d layer. More... | |
| class | CLConvertFullyConnectedWeights |
| Basic function to run an opencl::kernels::ClConvertFullyConnectedWeightsKernel. More... | |
| class | CLConvolutionLayer |
| Basic function to compute the convolution layer. More... | |
| class | CLCopy |
| Basic function to run opencl::kernels::ClCopyKernel. More... | |
| class | CLCrop |
| Basic function to run opencl::kernels::ClCropKernel. More... | |
| class | CLCropResize |
| Function to perform cropping and resizing. More... | |
| class | CLDeconvolutionLayer |
| Basic function to compute the deconvolution layer. More... | |
| class | CLDeconvolutionLayerUpsample |
| Basic function to execute deconvolution upsample on OpenCL. More... | |
| class | CLDeconvolutionLayerUpsampleKernel |
| Interface for the Deconvolution layer kernel on OpenCL. More... | |
| class | CLDeconvolutionReshapeOutputKernel |
| Interface for the OpenCL kernel to be used for reshaping the tensor before returning the result of deconvolution. More... | |
| class | CLDepthConvertLayer |
| Basic function to run opencl::kernels::ClCastKernel. More... | |
| class | CLDepthToSpaceLayer |
| Basic function to run CLDepthToSpaceLayerKernel. More... | |
| class | CLDepthToSpaceLayerKernel |
| Interface for the depth to space kernel. More... | |
| class | CLDepthwiseConvolutionLayer |
| Function to execute a depthwise convolution. More... | |
| class | CLDepthwiseConvolutionLayerNativeKernel |
| Interface for the kernel to run a MxN depthwise convolution. More... | |
| class | CLDequantizationLayer |
| Basic function to run opencl::ClDequantize that dequantizes an input tensor. More... | |
| class | CLDevice |
| OpenCL device type class. More... | |
| struct | CLDeviceOptions |
| OpenCL device options. More... | |
| class | CLDirectConvolutionLayer |
| Basic function to execute direct convolution function: More... | |
| class | CLDirectDeconvolutionLayer |
| Function to run the deconvolution layer. More... | |
| class | CLElementwiseMax |
| Basic function to run opencl::kernels::ClArithmeticKernel for max. More... | |
| class | CLElementwiseMin |
| Basic function to run opencl::kernels::ClArithmeticKernel for min. More... | |
| class | CLElementwisePower |
| Basic function to run opencl::kernels::ClArithmeticKernel for power. More... | |
| class | CLElementwiseSquaredDiff |
| Basic function to run opencl::kernels::ClArithmeticKernel for squared difference. More... | |
| class | CLExpLayer |
| Basic function to perform exponential on an input tensor. More... | |
| class | CLFFT1D |
| Basic function to execute one dimensional FFT. More... | |
| class | CLFFT2D |
| Basic function to execute two dimensional FFT. More... | |
| class | CLFFTConvolutionLayer |
| Basic function to execute FFT-based convolution on OpenCL. More... | |
| class | CLFFTDigitReverseKernel |
| Interface for the digit reverse operation kernel. More... | |
| class | CLFFTRadixStageKernel |
| Interface for the FFT radix stage kernel. More... | |
| class | CLFFTScaleKernel |
| Interface for the inverse fft scale kernel. More... | |
| class | CLFill |
| Basic function to run opencl::kernels::ClFillKernel. More... | |
| class | CLFillBorderKernel |
| Interface for filling the border of a kernel. More... | |
| class | CLFineSVMMemoryRegion |
| OpenCL fine-grain SVM memory region implementation. More... | |
| class | CLFlattenLayer |
| Basic function to execute flatten. More... | |
| class | CLFloor |
| Basic function to run opencl::kernels::ClFloorKernel. More... | |
| class | CLFullyConnectedLayer |
| Basic function to compute a Fully Connected layer on OpenCL. More... | |
| class | CLFuseBatchNormalization |
| Basic function to fuse the batch normalization node to a preceding convolution node. More... | |
| class | CLFuseBatchNormalizationKernel |
| OpenCL kernel to fuse the batch normalization node to a preceding convolution node. More... | |
| class | CLGather |
| Basic function to run CLGatherKernel. More... | |
| class | CLGatherKernel |
| Interface for the kernel to perform tensor reshaping. More... | |
| class | CLGEMM |
| Basic function to execute GEMM on OpenCL. More... | |
| class | CLGEMMConvolutionLayer |
| Basic function to compute the convolution layer. More... | |
| class | CLGEMMDeconvolutionLayer |
| Function to run the deconvolution layer through a call to GEMM. More... | |
| class | CLGEMMHeuristicsHandle |
| Handle for loading and retrieving GEMM heuristics. More... | |
| struct | CLGEMMKernelSelectionParams |
| OpenCL GEMM kernel selection parameters. More... | |
| class | CLGEMMLowpMatrixMultiplyCore |
| Basic function to execute GEMMLowpMatrixMultiplyCore on OpenCL. More... | |
| class | CLGEMMLowpOutputStage |
| Basic function to execute GEMMLowpQuantizeDown kernels on CL. More... | |
| class | CLGenerateProposalsLayer |
| Basic function to generate proposals for a RPN (Region Proposal Network) More... | |
| class | CLIndirectConvolutionLayer |
| Basic function to run the indirect convolution function. More... | |
| class | CLInstanceNormalizationLayer |
| Basic function to perform a Instance normalization. More... | |
| class | CLInstanceNormalizationLayerKernel |
| Interface for performing an instance normalization. More... | |
| class | CLKernelLibrary |
| CLKernelLibrary class. More... | |
| class | CLL2NormalizeLayer |
| Basic function to perform a L2 normalization on a given axis. More... | |
| class | CLL2NormalizeLayerKernel |
| Interface for performing a L2 normalize on a given axis given the square sum of it in this axis. More... | |
| class | CLLogicalAnd |
| Basic function to run arm_compute::opencl::kernels::ClLogicalBinaryKernel. More... | |
| class | CLLogicalNot |
| Basic function to do logical NOT operation. More... | |
| class | CLLogicalOr |
| Basic function to run arm_compute::opencl::kernels::ClLogicalBinaryKernel. More... | |
| class | CLLogLayer |
| Basic function to perform elementwise log on an input tensor. More... | |
| class | CLLSTMLayer |
| This function performs a single time step in a Long Short-Term Memory (LSTM) layer. More... | |
| class | CLLSTMLayerQuantized |
| Basic function to run CLLSTMLayerQuantized. More... | |
| class | CLMatMul |
| Basic function to execute MatMul (Matrix Multiplication) on OpenCL. More... | |
| class | CLMaxUnpoolingLayer |
| Function to perform MaxUnpooling. More... | |
| class | CLMaxUnpoolingLayerKernel |
| Interface for the pooling layer kernel. More... | |
| class | CLMeanStdDevNormalizationKernel |
| Interface for the kernel to normalize the input 2D tensor across the first dimension with respect to mean and standard deviation of the same dimension. More... | |
| class | CLMeanStdDevNormalizationLayer |
| Basic function to execute mean and standard deviation normalization by calling CLMeanStdDevNormalizationKernel. More... | |
| class | CLMemory |
| OpenCL implementation of memory object. More... | |
| class | CLMutableCommandBuffer |
| Command buffer implementaton based on CL mutable dispatch command buffer extension. More... | |
| class | CLNegLayer |
| Basic function to negate an input tensor. More... | |
| class | CLNormalizationLayer |
| Basic function to compute a normalization layer. More... | |
| class | CLNormalizationLayerKernel |
| Interface for the normalization layer kernel. More... | |
| class | CLNormalizePlanarYUVLayer |
| Basic function to run CLNormalizePlanarYUVLayerKernel. More... | |
| class | CLNormalizePlanarYUVLayerKernel |
| Interface for the NormalizePlanarYUV layer kernel. More... | |
| class | CLPadLayer |
| Basic function to pad a tensor. More... | |
| class | CLPadLayerKernel |
| Interface for the PadLayer function. More... | |
| class | CLPermute |
| Basic function to execute an opencl::kernels::ClPermuteKernel. More... | |
| class | CLPixelWiseMultiplication |
| Basic function to run opencl::ClMul. More... | |
| class | CLPooling3dLayer |
| Basic function to run opencl::ClPool3d. More... | |
| class | CLPoolingLayer |
| Basic function to run opencl::ClPool2d. More... | |
| class | CLPReluLayer |
| Basic function to run opencl::kernels::ClArithmeticKernel for PRELU. More... | |
| class | CLPriorBoxLayer |
| Basic function to run CLPriorBoxLayerKernel. More... | |
| class | CLPriorBoxLayerKernel |
| Interface for the PriorBox layer kernel. More... | |
| class | CLQLSTMLayer |
| Basic function to run CLQLSTMLayer. More... | |
| class | CLQLSTMLayerNormalizationKernel |
| Interface for the kernel to do layer normalization. More... | |
| struct | CLQuantization |
| OpenCL quantization data. More... | |
| class | CLQuantizationLayer |
| Basic function to simulate a quantization layer. More... | |
| class | CLRange |
| Basic function to run CLRangeKernel. More... | |
| class | CLRangeKernel |
| Kernel class for Range. More... | |
| class | CLReduceMean |
| Basic function to perform reduce operation. More... | |
| class | CLReductionOperation |
| Perform reduction operation. More... | |
| class | CLReductionOperationKernel |
| Interface for the reduction operation kernel. More... | |
| class | CLReorgLayer |
| class | CLReorgLayerKernel |
| OpenCL kernel to perform a reorg layer. More... | |
| class | CLReshapeLayer |
| Basic function to run opencl::kernels::ClReshapeKernel. More... | |
| class | CLReverse |
| Basic function to run CLReverseKernel. More... | |
| class | CLReverseKernel |
| Interface for the reverse kernel. More... | |
| class | CLRNNLayer |
| Basic function to run CLRNNLayer. More... | |
| class | CLROIAlignLayer |
| Basic function to run CLROIAlignLayerKernel. More... | |
| class | CLROIAlignLayerKernel |
| Interface for the RoIAlign kernel. More... | |
| class | CLROIPoolingLayer |
| Basic function to run CLROIPoolingLayerKernel. More... | |
| class | CLROIPoolingLayerKernel |
| Interface for the ROI pooling layer kernel. More... | |
| class | CLRoundLayer |
| Basic function to get the round (to the nearest even) value of an input tensor. More... | |
| class | CLRsqrtLayer |
| Basic function to perform inverse square root on an input tensor. More... | |
| class | CLRuntimeContext |
| Runtime context. More... | |
| class | CLScale |
| Basic function to run opencl::ClScale. More... | |
| class | CLScatter |
| Function to compute ScatterND Layer. More... | |
| class | CLScheduler |
| Provides global access to a CL context and command queue. More... | |
| class | CLSelect |
| Basic function to run CLSelect. More... | |
| class | CLSelectKernel |
| OpenCL interface for executing the select kernel. More... | |
| class | CLSinLayer |
| Basic function to calculate sine of an input tensor. More... | |
| class | CLSlice |
| Basic function to perform tensor slicing. More... | |
| class | CLSoftmaxLayerGeneric |
| Basic function to compute a SoftmaxLayer. More... | |
| class | CLSpaceToBatchLayer |
| Basic function to spatial divide a tensor. More... | |
| class | CLSpaceToBatchLayerKernel |
| Interface for the space to batch kernel. More... | |
| class | CLSpaceToDepthLayer |
| Basic function to run CLSpaceToDepthLayerKernel. More... | |
| class | CLSpaceToDepthLayerKernel |
| Interface for the space to depth kernel. More... | |
| class | CLSplit |
| Basic function to split a tensor along a given axis. More... | |
| class | CLStackLayer |
| Basic function to stack tensors along an axis. More... | |
| class | CLStackLayerKernel |
| OpenCL kernel to stacks a rank-R tensor into one with rank-(R+1) along the axis dimension. More... | |
| class | CLStridedSlice |
| Basic function to run CLStridedSliceKernel. More... | |
| class | CLStridedSliceKernel |
| Interface for the kernel to perform tensor strided slicing. More... | |
| class | CLSubTensor |
| Basic implementation of the OpenCL sub-tensor interface. More... | |
| class | CLSymbols |
| Class for loading OpenCL symbols. More... | |
| class | CLTensor |
| Basic implementation of the OpenCL tensor interface. More... | |
| class | CLTensorAllocator |
| Basic implementation of a CL memory tensor allocator. More... | |
| class | CLTile |
| Basic function to run CLTileKernel. More... | |
| class | CLTileKernel |
| OpenCL kernel to perform a Tile operation. More... | |
| class | CLTranspose |
| Basic function to execute an opencl::kernels::ClTransposeKernel. More... | |
| class | CLTuner |
| Basic implementation of the OpenCL tuner interface. More... | |
| struct | CLTuningInfo |
| class | CLTuningParams |
| < OpenCL tuner parameters More... | |
| class | CLUnstack |
| Basic function to unpack a rank-R tensor into rank-(R-1) tensors. More... | |
| class | CLWinogradConvolutionLayer |
| Basic function to execute Winograd-based convolution on OpenCL. More... | |
| class | ComputeAnchorsInfo |
| ComputeAnchors information class. More... | |
| struct | Conv2dInfo |
| Descriptor used by the 2d Convolution function. More... | |
| struct | Conv3dInfo |
| Descriptor used by the 3d Convolution function. More... | |
| struct | ConvolutionInfo |
| class | Coordinates |
| Coordinates of an item. More... | |
| struct | Coordinates2D |
| Coordinate type. More... | |
| struct | Coordinates3D |
| Coordinate type. More... | |
| class | CPPBoxWithNonMaximaSuppressionLimit |
| Basic function to run CPPBoxWithNonMaximaSuppressionLimitKernel. More... | |
| class | CPPBoxWithNonMaximaSuppressionLimitKernel |
| CPP kernel to perform computation of BoxWithNonMaximaSuppressionLimit. More... | |
| class | CPPDetectionOutputLayer |
| CPP Function to generate the detection output based on location and confidence predictions by doing non maximum suppression. More... | |
| class | CPPDetectionPostProcessLayer |
| CPP Function to generate the detection output based on center size encoded boxes, class prediction and anchors by doing non maximum suppression. More... | |
| class | CPPNonMaximumSuppression |
| CPP Function to perform non maximum suppression on the bounding boxes and scores. More... | |
| class | CPPNonMaximumSuppressionKernel |
| CPP Function to perform non maximum suppression on the bounding boxes and scores. More... | |
| class | CPPPermute |
| Basic function to run CPPPermuteKernel. More... | |
| class | CPPPermuteKernel |
| CPP kernel to perform tensor permutation. More... | |
| class | CPPScheduler |
| C++11 implementation of a pool of threads to automatically split a kernel's execution among several threads. More... | |
| class | CPPSplit |
| Basic function to split a tensor along a given axis. More... | |
| class | CPPTopKV |
| Basic function to run CPPTopKVKernel. More... | |
| class | CPPTopKVKernel |
| CPP kernel to perform tensor TopKV operation. More... | |
| class | CPPUpsample |
| Basic function to run CPPUpsample. More... | |
| class | CPPUpsampleKernel |
| CPP kernel to perform tensor upsample. More... | |
| class | CPUInfo |
| class | CpuMatMulSettings |
| Settings for MatMul Cpu implementation. More... | |
| class | DetectionOutputLayerInfo |
| Detection Output layer info. More... | |
| class | DetectionPostProcessLayerInfo |
| Detection Output layer info. More... | |
| struct | DetectionWindow |
| Detection window used for the object detection. More... | |
| class | Dimensions |
| Dimensions with dimensionality. More... | |
| struct | DirectConvComputeKernelInfo |
| Compute descriptor used by the direct convolution kernel. More... | |
| struct | DirectConvolutionLayerOutputStageKernelInfo |
| Descriptor used by the direct convolution layer output stage kernels. More... | |
| struct | DWCComputeKernelInfo |
| Compute descriptor used by the depthwise convolution native kernel. More... | |
| struct | enable_bitwise_ops |
| Disable bitwise operations by default. More... | |
| struct | enable_bitwise_ops< arm_compute::GPUTarget > |
| Enable bitwise operations on GPUTarget enumerations. More... | |
| struct | ErfLutEntry |
| Lookup table for erf(x) calculation. More... | |
| struct | FFT1DInfo |
| Descriptor used by the FFT1D function. More... | |
| struct | FFT2DInfo |
| Descriptor used by the FFT2D function. More... | |
| struct | FFTDigitReverseKernelInfo |
| Descriptor for FFT digit reverse kernels. More... | |
| struct | FFTRadixStageKernelInfo |
| Descriptor used by the FFT core kernels. More... | |
| struct | FFTScaleKernelInfo |
| Descriptor for FFT scale kernels. More... | |
| struct | FullyConnectedLayerInfo |
| Fully connected layer info. More... | |
| class | GEMMInfo |
| GEMM information class. More... | |
| struct | GEMMKernelInfo |
| Descriptor used by the GEMM kernels. More... | |
| struct | GEMMLHSMatrixInfo |
| GEMM LHS (Left Hand Side) matrix information. More... | |
| struct | GEMMLowpOutputStageInfo |
| GEMMLowp output stage info. More... | |
| struct | GEMMLowpReductionKernelInfo |
| class | GEMMReshapeInfo |
| GEMM reshape information class. More... | |
| struct | GEMMRHSMatrixInfo |
| GEMM RHS (Right Hand Side) matrix information. More... | |
| class | GenerateProposalsInfo |
| Generate Proposals Information class. More... | |
| class | GpuMatMulSettings |
| Settings for MatMul OpenCL implementation. More... | |
| class | IAccessWindow |
| Interface describing methods to update access window and padding based on kernel parameters. More... | |
| class | IAllocator |
| Allocator interface. More... | |
| class | IArray |
| Array of type T. More... | |
| class | IAssetManager |
| Asset manager interface. More... | |
| class | ICLArray |
| Interface for OpenCL Array. More... | |
| class | ICLKernel |
| Common interface for all the OpenCL kernels. More... | |
| class | ICLMemoryRegion |
| OpenCL memory region interface. More... | |
| class | ICLSimple2DKernel |
| Interface for simple OpenCL kernels having 1 tensor input and 1 tensor output. More... | |
| class | ICLSimple3DKernel |
| Interface for simple OpenCL kernels having 1 tensor input and 1 tensor output. More... | |
| class | ICLSimpleFunction |
| Basic interface for functions which have a single OpenCL kernel. More... | |
| class | ICLSimpleKernel |
| Interface for simple OpenCL kernels having 1 tensor input and 1 tensor output. More... | |
| class | ICLSVMMemoryRegion |
| OpenCL SVM memory region interface. More... | |
| class | ICLTensor |
| Interface for OpenCL tensor. More... | |
| class | ICLTuner |
| Basic interface for tuning the OpenCL kernels. More... | |
| class | IContext |
| Context interface. More... | |
| class | ICPPKernel |
| Common interface for all kernels implemented in C++. More... | |
| class | ICPPSimpleFunction |
| Basic interface for functions which have a single CPP kernel. More... | |
| class | IDevice |
| Interface for device object. More... | |
| class | IFunction |
| Base class for all functions. More... | |
| class | IKernel |
| Common information for all the kernels. More... | |
| class | ILifetimeManager |
| Interface for managing the lifetime of objects. More... | |
| class | IMemory |
| Memory interface. More... | |
| class | IMemoryGroup |
| Memory group interface. More... | |
| class | IMemoryManageable |
| Interface of an object than can be memory managed. More... | |
| class | IMemoryManager |
| Memory manager interface to handle allocations of backing memory. More... | |
| class | IMemoryPool |
| Memory Pool Inteface. More... | |
| class | IMemoryRegion |
| Memory region interface. More... | |
| class | INESimpleFunction |
| Basic interface for functions which have a single CPU kernel. More... | |
| class | INESimpleFunctionNoBorder |
| Basic interface for functions which have a single CPU kernel and no border. More... | |
| struct | InstanceNormalizationLayerKernelInfo |
| struct | IOFormatInfo |
| IO formatting information class. More... | |
| class | IOperator |
| Base class specifying the operator interface. More... | |
| class | IPoolManager |
| Memory pool manager interface. More... | |
| class | IQueue |
| Base class specifying the queue interface. More... | |
| class | IRuntimeContext |
| Context interface. More... | |
| class | IScheduler |
| Scheduler interface to run kernels. More... | |
| class | ISimpleLifetimeManager |
| Abstract class of the simple lifetime manager interface. More... | |
| class | ITensor |
| Interface for CPU tensor. More... | |
| class | ITensorAllocator |
| Interface to allocate tensors. More... | |
| class | ITensorInfo |
| Store the tensor's metadata. More... | |
| class | ITensorPack |
| Tensor packing service. More... | |
| class | ITensorV2 |
| Base class specifying the tensor interface. More... | |
| class | Iterator |
| Iterator updated by execute_window_loop for each window element. More... | |
| class | ITransformWeights |
| Weights tensor transform interface In order to identify the different reshape functions, each reshape function has to generate a unique id. More... | |
| class | IWeightsManager |
| Weights manager interface to handle weights transformations. More... | |
| class | Kernel |
| Kernel class. More... | |
| class | LSTMParams |
| struct | LUTInfo |
| class | LUTManager |
| class | MatMulInfo |
| Class for holding information related to matrix multiplication function. More... | |
| struct | MatMulKernelInfo |
| class | Memory |
| CPU implementation of memory object. More... | |
| class | MemoryGroup |
| Memory group. More... | |
| class | MemoryGroupResourceScope |
| Memory group resources scope handling class. More... | |
| class | MemoryManagerOnDemand |
| On-demand memory manager. More... | |
| class | MemoryRegion |
| Memory region CPU implementation. More... | |
| struct | MinMaxLocationValues |
| Min and max values and locations. More... | |
| class | NEActivationLayer |
| Basic function to run cpu::kernels::CpuActivationKernel. More... | |
| class | NEAddMulAdd |
| Function to compute Add+Mul+Add fused operation. More... | |
| class | NEArgMinMaxLayer |
| Function to calculate the index of the minimum or maximum values in a tensor based on an axis. More... | |
| class | NEArithmeticAddition |
| Basic function to run cpu::kernels::CpuAddKernel. More... | |
| class | NEArithmeticSubtraction |
| Basic function to run cpu::kernels::CpuSubKernel. More... | |
| class | NEBatchNormalizationLayer |
| Basic function to run NENormalizationLayerKernel and simulate a batch normalization layer. More... | |
| class | NEBatchNormalizationLayerKernel |
| Interface for the batch normalization layer kernel. More... | |
| class | NEBatchToSpaceLayer |
| Basic function to run NEBatchToSpaceLayerKernel. More... | |
| class | NEBatchToSpaceLayerKernel |
| Interface for the batch to space kernel. More... | |
| class | NEBitwiseAnd |
| Basic function to run NEBitwiseAndKernel. More... | |
| class | NEBitwiseAndKernel |
| Interface for the kernel to perform bitwise AND between XY-planes of two tensors. More... | |
| class | NEBitwiseNot |
| Basic function to run NEBitwiseNotKernel. More... | |
| class | NEBitwiseNotKernel |
| Interface for the kernel to perform bitwise NOT operation. More... | |
| class | NEBitwiseOr |
| Basic function to run NEBitwiseOrKernel. More... | |
| class | NEBitwiseOrKernel |
| Interface for the kernel to perform bitwise inclusive OR between two tensors. More... | |
| class | NEBitwiseXor |
| Basic function to run NEBitwiseXorKernel. More... | |
| class | NEBitwiseXorKernel |
| Interface for the kernel to perform bitwise exclusive OR (XOR) between two tensors. More... | |
| class | NEBoundingBoxTransform |
| Basic function to run NEBoundingBoxTransformKernel. More... | |
| class | NEBoundingBoxTransformKernel |
| Interface for the bounding box kernel. More... | |
| class | NECast |
| Basic function to run cpu::kernels::CpuCastKernel. More... | |
| class | NEChannelShuffleLayer |
| Basic function to run NEChannelShuffleLayerKernel. More... | |
| class | NEChannelShuffleLayerKernel |
| Interface for the channel shuffle kernel. More... | |
| class | NECol2ImKernel |
| Kernel to perform col2im reshaping. More... | |
| class | NEComplexPixelWiseMultiplication |
| Basic function to run cpu::CpuComplexMul. More... | |
| class | NEComputeAllAnchorsKernel |
| Interface for Compute All Anchors kernel. More... | |
| class | NEConcatenateLayer |
| Basic function to execute concatenate tensors along a given axis. More... | |
| class | NEConv3D |
| Basic function to simulate a 3d convolution. More... | |
| class | NEConvertFullyConnectedWeights |
| Basic function to run cpu::kernels::CpuConvertFullyConnectedWeightsKernel. More... | |
| class | NEConvolutionLayer |
| Basic function to simulate a convolution layer. More... | |
| class | NECopy |
| Basic function to run cpu::kernels::CpuCopyKernel. More... | |
| class | NECropKernel |
| Interface for the kernel to perform tensor cropping. More... | |
| class | NECropResize |
| Function to perform cropping and resizing. More... | |
| class | NEDeconvolutionLayer |
| Function to run the deconvolution layer. More... | |
| class | NEDepthConvertLayer |
| Basic function to run cpu::kernels::CpuCastKernel. More... | |
| class | NEDepthToSpaceLayer |
| Basic function to run NEDepthToSpaceLayerKernel. More... | |
| class | NEDepthToSpaceLayerKernel |
| Interface for the depth to space kernel. More... | |
| class | NEDepthwiseConvolutionLayer |
| Function to execute a depthwise convolution. More... | |
| class | NEDequantizationLayer |
| Basic function to run cpu::CpuDequantize that dequantizes an input tensor. More... | |
| class | NEDetectionPostProcessLayer |
| NE Function to generate the detection output based on center size encoded boxes, class prediction and anchors by doing non maximum suppression. More... | |
| class | NEDirectConvolutionLayer |
| Function to run the direct convolution. More... | |
| class | NEElementwiseComparison |
| Basic function to run cpu::kernels::CpuComparisonKernel. More... | |
| class | NEElementwiseComparisonStatic |
| Basic function to run cpu::kernels::CpuComparisonKernel. More... | |
| class | NEElementwiseDivision |
| Basic function to run cpu::kernels::CpuArithmeticKernel for division. More... | |
| class | NEElementwiseMax |
| Basic function to run cpu::kernels::CpuArithmeticKernel for max. More... | |
| class | NEElementwiseMin |
| Basic function to run cpu::kernels::CpuArithmeticKernel for min. More... | |
| class | NEElementwisePower |
| Basic function to run cpu::kernels::CpuArithmeticKernel for power. More... | |
| class | NEElementwiseSquaredDiff |
| Basic function to run cpu::kernels::CpuArithmeticKernel for squared difference. More... | |
| class | NEElementwiseUnaryLayer |
| Basic function to perform unary elementwise operations. More... | |
| class | NEFFT1D |
| Basic function to execute one dimensional FFT. More... | |
| class | NEFFT2D |
| Basic function to execute two dimensional FFT. More... | |
| class | NEFFTConvolutionLayer |
| Basic function to execute FFT-based convolution on CPU. More... | |
| class | NEFFTDigitReverseKernel |
| Interface for the digit reverse operation kernel. More... | |
| class | NEFFTRadixStageKernel |
| Interface for the FFT kernel. More... | |
| class | NEFFTScaleKernel |
| Interface for the inverse fft scale kernel. More... | |
| class | NEFill |
| Basic function to run cpu::kernels::CpuFillKernel. More... | |
| class | NEFillBorder |
| Basic function to run NEFillBorderKernel. More... | |
| class | NEFillBorderKernel |
| Interface for the kernel to fill borders. More... | |
| class | NEFlattenLayer |
| Basic function to execute flatten layer kernel. More... | |
| class | NEFloor |
| Basic function to run cpu::kernels::CpuFloorKernel. More... | |
| class | NEFullyConnectedLayer |
| Basic function to compute a Fully Connected layer. More... | |
| class | NEFuseBatchNormalization |
| Basic function to fuse the batch normalization node to a preceding convolution node. More... | |
| class | NEFuseBatchNormalizationKernel |
| OpenNE kernel to fuse the batch normalization node to a preceding convolution node. More... | |
| class | NEGather |
| Basic function to run NEGatherKernel. More... | |
| class | NEGatherKernel |
| Kernel to perform gather operation. More... | |
| class | NEGEMM |
| Basic function to execute GEMM. More... | |
| class | NEGEMMConv2d |
| Basic function to compute the convolution layer. More... | |
| class | NEGEMMConvolutionLayer |
| Basic function to compute the convolution layer. More... | |
| class | NEGEMMLowpMatrixMultiplyCore |
| Function to run Gemm on quantized types. More... | |
| class | NEGEMMLowpOutputStage |
| Basic function to execute GEMMLowpQuantizeDown kernels. More... | |
| class | NEGenerateProposalsLayer |
| Basic function to generate proposals for a RPN (Region Proposal Network) More... | |
| class | NEInstanceNormalizationLayer |
| Basic function to perform a Instance normalization. More... | |
| class | NEInstanceNormalizationLayerKernel |
| Interface for performing an instance normalization. More... | |
| class | NEL2NormalizeLayer |
| Basic function to perform a L2 normalization on a given axis. More... | |
| class | NEL2NormalizeLayerKernel |
| Interface for performing a L2 normalize on a given axis given the square sum of it in this axis. More... | |
| class | NELogicalAnd |
| Basic function to perform logical AND. More... | |
| class | NELogicalNot |
| Basic function to perform logical NOT. More... | |
| class | NELogicalOr |
| Basic function to perform logical OR. More... | |
| class | NELSTMLayer |
| Basic function to run NELSTMLayer. More... | |
| class | NELSTMLayerQuantized |
| Basic function to run NELSTMLayerQuantized. More... | |
| class | NEMatMul |
| Basic function to run the following operators: More... | |
| class | NEMaxUnpoolingLayer |
| Function to perform MaxUnpooling. More... | |
| class | NEMeanStdDevNormalizationKernel |
| Interface for the kernel to normalize the input 2D tensor across the first dimension with respect to mean and standard deviation of the same dimension. More... | |
| class | NEMeanStdDevNormalizationLayer |
| Basic function to execute mean and standard deviation normalization by calling NEMeanStdDevNormalizationKernel. More... | |
| class | NENormalizationLayer |
| Basic function to compute a normalization layer. More... | |
| class | NENormalizationLayerKernel |
| Interface for the normalization layer kernel. More... | |
| class | NEPadLayer |
| Basic function to pad a tensor. More... | |
| class | NEPadLayerKernel |
| Basic kernel to pad the input tensor given padding information. More... | |
| class | NEPermute |
| Basic function to run cpu::kernels::CpuPermuteKernel. More... | |
| class | NEPixelWiseMultiplication |
| Basic function to run cpu::CpuMul. More... | |
| class | NEPooling3dLayer |
| Basic function to simulate a pooling 3d layer with the specified pooling operation. More... | |
| class | NEPoolingLayer |
| Basic function to simulate a pooling layer with the specified pooling operation. More... | |
| class | NEPReluLayer |
| Basic function to run cpu::kernels::CpuArithmeticKernel for PRELU. More... | |
| class | NEPriorBoxLayer |
| Basic function to run NEPriorBoxLayerKernel. More... | |
| class | NEPriorBoxLayerKernel |
| Interface for the kernel to calculate prior boxes. More... | |
| class | NEQLSTMLayer |
| Basic function to run NEQLSTMLayer. More... | |
| class | NEQLSTMLayerNormalizationKernel |
| Kernel to perform layer normalization for QLSTM. More... | |
| class | NEQuantizationLayer |
| Basic function to run a quantization layer using cpu::CpuQuantize. More... | |
| class | NERange |
| Basic function to run NERangeKernel. More... | |
| class | NERangeKernel |
| Kernel class for Range. More... | |
| class | NEReduceMean |
| Basic function to perform reduce operation. More... | |
| class | NEReductionOperation |
| Basic function to simulate a reduction operation. More... | |
| class | NEReductionOperationKernel |
| Kernel to perform a reduction operation. More... | |
| class | NEReorgLayer |
| Basic function to run NEReorgLayerKernel. More... | |
| class | NEReorgLayerKernel |
| Interface for the kernel to perform tensor re-organization. More... | |
| class | NEReshapeLayer |
| Basic function to run cpu::kernels::CpuReshapeKernel. More... | |
| class | NEReverse |
| Basic function to run NEReverseKernel. More... | |
| class | NEReverseKernel |
| Interface for the reverse layer kernel. More... | |
| class | NERNNLayer |
| Basic function to run NERNNLayer. More... | |
| class | NEROIAlignLayer |
| Basic function to run NEROIAlignLayerKernel. More... | |
| class | NEROIAlignLayerKernel |
| Interface for the RoIAlign kernel. More... | |
| class | NEROIPoolingLayer |
| Basic function to run NEROIPoolingLayerKernel. More... | |
| class | NEROIPoolingLayerKernel |
| Interface for the ROI pooling layer kernel. More... | |
| class | NEScale |
| Basic function to compute Scale. More... | |
| class | NESelect |
| Basic function to run NESelect. More... | |
| class | NESelectKernel |
| Interface for the select kernel. More... | |
| class | NESlice |
| Basic function to perform tensor slicing. More... | |
| class | NESoftmaxLayerGeneric |
| Basic function to compute a SoftmaxLayer and a Log SoftmaxLayer. More... | |
| class | NESpaceToBatchLayer |
| Basic function to spatial divide a tensor. More... | |
| class | NESpaceToBatchLayerKernel |
| Interface for the space to batch kernel. More... | |
| class | NESpaceToDepthLayer |
| Basic function to run NESpaceToDepthLayerKernel. More... | |
| class | NESpaceToDepthLayerKernel |
| Interface for the space to depth kernel. More... | |
| class | NESplit |
| Basic function to split a tensor along a given axis. More... | |
| class | NEStackLayer |
| Basic function to stack tensors along an axis. More... | |
| class | NEStackLayerKernel |
| Basic kernel to stack a rank-R tensor into one with rank-(R+1) along the axis dimension. More... | |
| class | NEStridedSlice |
| Basic function to run NEStridedSliceKernel. More... | |
| class | NEStridedSliceKernel |
| Interface for the kernel to perform tensor strided slicing. More... | |
| class | NETile |
| Basic function to run NETileKernel. More... | |
| class | NETileKernel |
| Basic kernel to perform a tile operation. More... | |
| class | NETranspose |
| Basic function to run cpu::kernels::CpuTransposeKernel. More... | |
| class | NEUnstack |
| Basic function to unpack a rank-R tensor into rank-(R-1) tensors. More... | |
| class | NEWinogradConvolutionLayer |
| Basic function to simulate a convolution layer. More... | |
| class | NormalizationLayerInfo |
| Normalization Layer Information class. More... | |
| class | OffsetLifetimeManager |
| Concrete class that tracks the lifetime of registered tensors and calculates the systems memory requirements in terms of a single blob and a list of offsets. More... | |
| class | OffsetMemoryPool |
| Offset based memory pool. More... | |
| class | OMPScheduler |
| Pool of threads to automatically split a kernel's execution among several threads. More... | |
| struct | Padding2D |
| Padding and stride information class. More... | |
| struct | Padding3D |
| Padding information for 3D operations like Conv3d. More... | |
| class | PadStrideInfo |
| class | PixelValue |
| Class describing the value of a pixel for any image format. More... | |
| struct | Pooling3dLayerInfo |
| Pooling Layer Information struct. More... | |
| struct | PoolingLayerInfo |
| Pooling Layer Information struct. More... | |
| class | PoolManager |
| Memory pool manager. More... | |
| class | PriorBoxLayerInfo |
| PriorBox layer info. More... | |
| class | Program |
| Program class. More... | |
| struct | Qasymm8QuantizationHelper |
| class | QuantizationInfo |
| Quantization information. More... | |
| struct | Rectangle |
| Rectangle type. More... | |
| class | ROIPoolingLayerInfo |
| ROI Pooling Layer Information class. More... | |
| class | RuntimeContext |
| Runtime context. More... | |
| struct | ScaleKernelInfo |
| struct | ScatterInfo |
| Scatter operator information. More... | |
| class | Scheduler |
| Configurable scheduler which supports multiple multithreading APIs and choosing between different schedulers at runtime. More... | |
| class | SchedulerFactory |
| Scheduler Factory. More... | |
| class | Semaphore |
| Semamphore class. More... | |
| class | SingleThreadScheduler |
| Pool of threads to automatically split a kernel's execution among several threads. More... | |
| class | Size2D |
| Class for specifying the size of an image or rectangle. More... | |
| class | Size3D |
| Class for specifying the size of a 3D shape or object. More... | |
| struct | SoftmaxKernelInfo |
| Descriptor used by the softmax kernels. More... | |
| class | Status |
| Status class. More... | |
| class | Steps |
| Class to describe a number of elements in each dimension. More... | |
| class | StridedSliceLayerInfo |
| class | Strides |
| Strides of an item in bytes. More... | |
| class | SubTensor |
| Basic implementation of the sub-tensor interface. More... | |
| class | SubTensorInfo |
| Store the sub tensor's metadata. More... | |
| class | Tensor |
| Basic implementation of the tensor interface. More... | |
| class | TensorAccessor |
| Tensor accessors to make it easier to interface with arm_gemm. More... | |
| class | TensorAllocator |
| Basic implementation of a CPU memory tensor allocator. More... | |
| class | TensorInfo |
| Store the tensor's metadata. More... | |
| class | TensorPack |
| Tensor packing service. More... | |
| class | TensorShape |
| Shape of a tensor. More... | |
| struct | ThreadInfo |
| Information about executing thread and CPU. More... | |
| struct | UniformQuantizationInfo |
| Quantization info when assuming per layer quantization. More... | |
| struct | ValidRegion |
| Container for valid region of a window. More... | |
| class | WeightsInfo |
| Convolution Layer Weights Information class. More... | |
| class | Window |
| Describe a multidimensional execution window. More... | |
| class | WindowIterator |
| Iterate over a portion of a Window. More... | |
| struct | WinogradInfo |
| Winograd information. More... | |
| struct | WorkspaceDataElement |
Typedefs | |
| using | ICLUInt8Array = ICLArray< cl_uchar > |
| Interface for OpenCL Array of uint8s. More... | |
| using | ICLUInt16Array = ICLArray< cl_ushort > |
| Interface for OpenCL Array of uint16s. More... | |
| using | ICLUInt32Array = ICLArray< cl_uint > |
| Interface for OpenCL Array of uint32s. More... | |
| using | ICLInt16Array = ICLArray< cl_short > |
| Interface for OpenCL Array of int16s. More... | |
| using | ICLInt32Array = ICLArray< cl_int > |
| Interface for OpenCL Array of int32s. More... | |
| using | ICLFloatArray = ICLArray< cl_float > |
| Interface for OpenCL Array of floats. More... | |
| using | ICLImage = ICLTensor |
| using | half = half_float::half |
| 16-bit floating point type More... | |
| using | PermutationVector = Strides |
| Permutation vector. More... | |
| using | IUInt8Array = IArray< uint8_t > |
| Interface for Array of uint8s. More... | |
| using | IUInt16Array = IArray< uint16_t > |
| Interface for Array of uint16s. More... | |
| using | IUInt32Array = IArray< uint32_t > |
| Interface for Array of uint32s. More... | |
| using | IInt16Array = IArray< int16_t > |
| Interface for Array of int16s. More... | |
| using | IInt32Array = IArray< int32_t > |
| Interface for Array of int32s. More... | |
| using | IFloatArray = IArray< float > |
| Interface for Array of floats. More... | |
| using | IImage = ITensor |
| using | qasymm8_signed_t = int8_t |
| 8 bit signed quantized asymmetric scalar value More... | |
| using | qasymm8_t = uint8_t |
| 8 bit quantized asymmetric scalar value More... | |
| using | qsymm16_t = int16_t |
| 16 bit quantized symmetric scalar value More... | |
| using | qasymm16_t = uint16_t |
| 16 bit quantized asymmetric scalar value More... | |
| using | BiStrides = Coordinates |
| Bidirectional strides. More... | |
| using | PaddingSize = BorderSize |
| Container for 2D padding size. More... | |
| using | PaddingInfo = std::pair< uint32_t, uint32_t > |
| Padding information as a pair of unsigned int start/end. More... | |
| using | PaddingList = std::vector< PaddingInfo > |
| List of padding information. More... | |
| using | Multiples = std::vector< uint32_t > |
| Information to produce a tiled version of a Tensor. More... | |
| using | BBox = std::array< float, 4 > |
| using | LabelBBox = std::map< int, std::vector< BBox > > |
| using | CropInfo = Padding2D |
| Class for holding information related to cropping. More... | |
| using | UInt8Array = Array< uint8_t > |
| Array of uint8s. More... | |
| using | UInt16Array = Array< uint16_t > |
| Array of uint16s. More... | |
| using | UInt32Array = Array< uint32_t > |
| Array of uint32s. More... | |
| using | Int16Array = Array< int16_t > |
| Array of int16s. More... | |
| using | Int32Array = Array< int32_t > |
| Array of int32s. More... | |
| using | FloatArray = Array< float > |
| Array of floats. More... | |
| using | CLUInt8Array = CLArray< cl_uchar > |
| OpenCL Array of uint8s. More... | |
| using | CLUInt16Array = CLArray< cl_ushort > |
| OpenCL Array of uint16s. More... | |
| using | CLUInt32Array = CLArray< cl_uint > |
| OpenCL Array of uint32s. More... | |
| using | CLInt16Array = CLArray< cl_short > |
| OpenCL Array of int16s. More... | |
| using | CLInt32Array = CLArray< cl_int > |
| OpenCL Array of int32s. More... | |
| using | CLFloatArray = CLArray< cl_float > |
| OpenCL Array of floats. More... | |
| using | CLImage = CLTensor |
| OpenCL Image. More... | |
| using | CLEqual = CLComparisonStatic< ComparisonOperation::Equal > |
| Basic function to run equal comparison. More... | |
| using | CLNotEqual = CLComparisonStatic< ComparisonOperation::NotEqual > |
| Basic function to run not equal comparison. More... | |
| using | CLGreater = CLComparisonStatic< ComparisonOperation::Greater > |
| Basic function to run greater comparison. More... | |
| using | CLGreaterEqual = CLComparisonStatic< ComparisonOperation::GreaterEqual > |
| Basic function to run greater-equal comparison. More... | |
| using | CLLess = CLComparisonStatic< ComparisonOperation::Less > |
| Basic function to run less comparison. More... | |
| using | CLLessEqual = CLComparisonStatic< ComparisonOperation::LessEqual > |
| Basic function to run less-equal comparison. More... | |
| using | CLSoftmaxLayer = CLSoftmaxLayerGeneric< false > |
| using | CLLogSoftmaxLayer = CLSoftmaxLayerGeneric< true > |
| using | NEEqual = NEElementwiseComparisonStatic< ComparisonOperation::Equal > |
| Basic function to run equal comparison. More... | |
| using | NENotEqual = NEElementwiseComparisonStatic< ComparisonOperation::NotEqual > |
| Basic function to run not equal comparison. More... | |
| using | NEGreater = NEElementwiseComparisonStatic< ComparisonOperation::Greater > |
| Basic function to run greater comparison. More... | |
| using | NEGreaterEqual = NEElementwiseComparisonStatic< ComparisonOperation::GreaterEqual > |
| Basic function to run greater-equal comparison. More... | |
| using | NELess = NEElementwiseComparisonStatic< ComparisonOperation::Less > |
| Basic function to run less comparison. More... | |
| using | NELessEqual = NEElementwiseComparisonStatic< ComparisonOperation::LessEqual > |
| Basic function to run less-equal comparison. More... | |
| using | NERsqrtLayer = NEElementwiseUnaryLayer< ElementWiseUnary::RSQRT > |
| using | NEExpLayer = NEElementwiseUnaryLayer< ElementWiseUnary::EXP > |
| using | NENegLayer = NEElementwiseUnaryLayer< ElementWiseUnary::NEG > |
| using | NELogLayer = NEElementwiseUnaryLayer< ElementWiseUnary::LOG > |
| using | NEAbsLayer = NEElementwiseUnaryLayer< ElementWiseUnary::ABS > |
| using | NERoundLayer = NEElementwiseUnaryLayer< ElementWiseUnary::ROUND > |
| using | NESinLayer = NEElementwiseUnaryLayer< ElementWiseUnary::SIN > |
| using | NESoftmaxLayer = NESoftmaxLayerGeneric< false > |
| using | NELogSoftmaxLayer = NESoftmaxLayerGeneric< true > |
| using | INEKernel = ICPPKernel |
| Common interface for all kernels implemented in Neon. More... | |
| using | NEScheduler = Scheduler |
| CPU Scheduler. More... | |
| using | Image = Tensor |
| Image. More... | |
| using | MemoryMappings = std::map< IMemory *, size_t > |
| A map of (handle, index/offset), where handle is the memory handle of the object to provide the memory for and index/offset is the buffer/offset from the pool that should be used. More... | |
| using | GroupMappings = std::map< size_t, MemoryMappings > |
| A map of the groups and memory mappings. More... | |
| using | MemoryRequirements = experimental::MemoryRequirements |
| template<typename TensorType > | |
| using | WorkspaceData = std::vector< WorkspaceDataElement< TensorType > > |
| using | qasymm8x8_t = uint8x8_t |
| 8 bit quantized asymmetric vector with 8 elements More... | |
| using | qasymm8x8x2_t = uint8x8x2_t |
| 8 bit quantized asymmetric vector with 16 elements More... | |
| using | qasymm8x8x3_t = uint8x8x3_t |
| 8 bit quantized asymmetric vector with 24 elements More... | |
| using | qasymm8x8x4_t = uint8x8x4_t |
| 8 bit quantized asymmetric vector with 32 elements More... | |
| using | qasymm8x16_t = uint8x16_t |
| 8 bit quantized asymmetric vector with 16 elements More... | |
| using | qasymm8x8_signed_t = int8x8_t |
| 8 bit quantized signed asymmetric vector with 8 elements More... | |
| using | qasymm8x8x2_signed_t = int8x8x2_t |
| 8 bit quantized signed asymmetric vector with 16 elements More... | |
| using | qasymm8x8x3_signed_t = int8x8x3_t |
| 8 bit quantized signed asymmetric vector with 24 elements More... | |
| using | qasymm8x8x4_signed_t = int8x8x4_t |
| 8 bit quantized signed asymmetric vector with 32 elements More... | |
| using | qasymm8x16_signed_t = int8x16_t |
| 8 bit quantized signed asymmetric vector with 16 elements More... | |
| using | qsymm8_t = int8_t |
| 8 bit quantized symmetric scalar value More... | |
| using | qsymm16x8_t = int16x8_t |
| 16 bit quantized symmetric vector with 8 elements More... | |
| using | qsymm16x8x2_t = int16x8x2_t |
| 16 bit quantized symmetric vector with 16 elements More... | |
| typedef float | float32_t |
| using | OperatorType = opencl::ClGemm |
| using | Mutex = std::mutex |
| Wrapper of Mutex data-object. More... | |
| template<typename Mutex > | |
| using | lock_guard = std::lock_guard< Mutex > |
| Wrapper of lock_guard data-object. More... | |
| template<typename Mutex > | |
| using | unique_lock = std::unique_lock< Mutex > |
| Wrapper of lock_guard data-object. More... | |
Enumerations | |
| enum | CLVersion { CL10, CL11, CL12, CL20, CL30, UNKNOWN } |
| Available OpenCL Version. More... | |
| enum | CLKernelType { UNKNOWN, UNKNOWN, DEPTHWISE, DIRECT, ELEMENTWISE, GEMM, POOL, WINOGRAD } |
| enum | Channel { UNKNOWN, C0, C1, C2, C3, R, G, B, A, Y, U, V } |
| Available channels. More... | |
| enum | Format { UNKNOWN, U8, S16, U16, S32, U32, S64, U64, BFLOAT16, F16, F32, UV88, RGB888, RGBA8888, YUV444, YUYV422, NV12, NV21, IYUV, UYVY422 } |
| Image colour formats. More... | |
| enum | DataType { UNKNOWN, U8, S8, QSYMM8, QASYMM8, QASYMM8_SIGNED, QSYMM8_PER_CHANNEL, U16, S16, QSYMM16, QASYMM16, U32, S32, U64, S64, BFLOAT16, F16, F32, F64, SIZET } |
| Available data types. More... | |
| enum | DataLayout { UNKNOWN, NCHW, NHWC, NCDHW, NDHWC } |
| [DataLayout enum definition] More... | |
| enum | DataLayoutDimension { CHANNEL, HEIGHT, WIDTH, DEPTH, BATCHES } |
| [DataLayout enum definition] More... | |
| enum | DimensionRoundingType { FLOOR, CEIL } |
| Dimension rounding type when down-scaling on CNNs. More... | |
| enum | WeightFormat { UNSPECIFIED = 0x1, ANY = 0x2, OHWI = 0x100100, OHWIo2 = 0x100200, OHWIo4 = 0x100400, OHWIo8 = 0x100800, OHWIo16 = 0x101000, OHWIo32 = 0x102000, OHWIo64 = 0x104000, OHWIo128 = 0x108000, OHWIo4i2 = 0x200400, OHWIo4i2_bf16 = 0x200410, OHWIo8i2 = 0x200800, OHWIo8i2_bf16 = 0x200810, OHWIo16i2 = 0x201000, OHWIo16i2_bf16 = 0x201010, OHWIo32i2 = 0x202000, OHWIo32i2_bf16 = 0x202010, OHWIo64i2 = 0x204000, OHWIo64i2_bf16 = 0x204010, OHWIo4i4 = 0x400400, OHWIo4i4_bf16 = 0x400410, OHWIo8i4 = 0x400800, OHWIo8i4_bf16 = 0x400810, OHWIo16i4 = 0x401000, OHWIo16i4_bf16 = 0x401010, OHWIo32i4 = 0x402000, OHWIo32i4_bf16 = 0x402010, OHWIo64i4 = 0x404000, OHWIo64i4_bf16 = 0x404010, OHWIo2i8 = 0x800200, OHWIo4i8 = 0x800400, OHWIo8i8 = 0x800800, OHWIo16i8 = 0x801000, OHWIo32i8 = 0x802000, OHWIo64i8 = 0x804000 } |
| Memory layouts for the weights tensor. More... | |
| enum | CPUModel { X, GENERIC, GENERIC_FP16, GENERIC_FP16_DOT, A53, A55r0, A55r1, A35, A73, A76, A510, X1, V1, A64FX, N1 } |
| CPU models types. More... | |
| enum | ErrorCode { OK, RUNTIME_ERROR, UNSUPPORTED_EXTENSION_USE } |
| Available error codes. More... | |
| enum | TensorType : int32_t { ACL_UNKNOWN = -1, ACL_SRC_DST = 0, ACL_SRC = 0, ACL_SRC_0 = 0, ACL_SRC_1 = 1, ACL_SRC_2 = 2, ACL_SRC_3 = 3, ACL_SRC_4 = 4, ACL_SRC_5 = 5, ACL_SRC_6 = 6, ACL_SRC_END = 6, ACL_DST = 30, ACL_DST_0 = 30, ACL_DST_1 = 31, ACL_DST_2 = 32, ACL_DST_END = 32, ACL_INT = 50, ACL_INT_0 = 50, ACL_INT_1 = 51, ACL_INT_2 = 52, ACL_INT_3 = 53, ACL_INT_4 = 54, ACL_SRC_VEC = 256, ACL_DST_VEC = 512, ACL_INT_VEC = 1024, ACL_BIAS = ACL_SRC_2, ACL_VEC_ROW_SUM = ACL_SRC_3, ACL_VEC_COL_SUM = ACL_SRC_4, ACL_SHIFTS = ACL_SRC_5, ACL_MULTIPLIERS = ACL_SRC_6 } |
| Memory type. More... | |
| enum | GPUTarget { UNKNOWN = 0x101, GPU_ARCH_MASK = 0xF00, GPU_GENERATION_MASK = 0x0F0, MIDGARD = 0x100, BIFROST = 0x200, VALHALL = 0x300, FIFTHGEN = 0X400, T600 = 0x110, T700 = 0x120, T800 = 0x130, G71 = 0x210, G72 = 0x220, G51 = 0x221, G51BIG = 0x222, G51LIT = 0x223, G31 = 0x224, G76 = 0x230, G52 = 0x231, G52LIT = 0x232, G77 = 0x310, G57 = 0x311, G78 = 0x320, G68 = 0x321, G78AE = 0x330, G710 = 0x340, G610 = 0x341, G510 = 0x342, G310 = 0x343, G715 = 0x350, G615 = 0x351, G720 = 0x410, G620 = 0X411 } |
| Available GPU Targets. More... | |
| enum | DeviceType { NEON, CL } |
| Device types. More... | |
| enum | RoundingPolicy { TO_ZERO, TO_NEAREST_UP, TO_NEAREST_EVEN } |
| Rounding method. More... | |
| enum | SamplingPolicy { CENTER, TOP_LEFT } |
| Available Sampling Policies. More... | |
| enum | ConvolutionMethod { GEMM, GEMM_CONV2D, DIRECT, INDIRECT, WINOGRAD, FFT } |
| Available ConvolutionMethod. More... | |
| enum | DepthwiseConvolutionFunction { OPTIMIZED, GENERIC } |
| Available DepthwiseConvolutionFunction. More... | |
| enum | DeconvolutionMethod { GEMM, DIRECT, UPSCALE_CONV2D } |
| Available DeconvolutionMethod. More... | |
| enum | FuseBatchNormalizationType { CONVOLUTION, DEPTHWISECONVOLUTION } |
| Available FuseBatchNormalizationType. More... | |
| enum | PaddingMode { CONSTANT, REFLECT, SYMMETRIC } |
| Padding mode to use for PadLayer. More... | |
| enum | ComparisonOperation { Equal, NotEqual, Greater, GreaterEqual, Less, LessEqual } |
| Supported comparison operations. More... | |
| enum | BorderMode { UNDEFINED, CONSTANT, REPLICATE } |
| Methods available to handle borders. More... | |
| enum | ConvertPolicy { WRAP, SATURATE } |
| Policy to handle integer overflow. More... | |
| enum | InterpolationPolicy { NEAREST_NEIGHBOR, BILINEAR, AREA } |
| Interpolation method. More... | |
| enum | BilinearInterpolation { BILINEAR_OLD_NEW, BILINEAR_SCHARR } |
| Bilinear Interpolation method used by LKTracker. More... | |
| enum | ReductionOperation { ARG_IDX_MAX, ARG_IDX_MIN, MEAN_SUM, PROD, SUM_SQUARE, SUM, MIN, MAX } |
| Available reduction operations. More... | |
| enum | ArithmeticOperation { ADD, SUB, DIV, MIN, MAX, SQUARED_DIFF, POWER, PRELU } |
| Available element-wise operations. More... | |
| enum | ElementWiseUnary { RSQRT, EXP, NEG, LOG, ABS, SIN, ROUND, LOGICAL_NOT } |
| Available element wise unary operations. More... | |
| enum | BitwiseOperation { AND, NOT, OR, XOR } |
| Available bitwise operations. More... | |
| enum | NormType { IN_MAP_1D, IN_MAP_2D, CROSS_MAP } |
| The normalization type used for the normalization layer. More... | |
| enum | PoolingType { MAX, AVG, L2 } |
| Available pooling types. More... | |
| enum | NMSType { LINEAR, GAUSSIAN, ORIGINAL } |
| Available non maxima suppression types. More... | |
| enum | DetectionOutputLayerCodeType { CORNER, CENTER_SIZE, CORNER_SIZE, TF_CENTER } |
| Available Detection Output code types. More... | |
| enum | ActivationFunction { LOGISTIC, TANH, RELU, BOUNDED_RELU, LU_BOUNDED_RELU, LEAKY_RELU, SOFT_RELU, ELU, ABS, SQUARE, SQRT, LINEAR, IDENTITY, HARD_SWISH, SWISH, GELU } |
| Available activation functions. More... | |
| enum | GEMMLowpOutputStageType { NONE, QUANTIZE_DOWN, QUANTIZE_DOWN_FIXEDPOINT, QUANTIZE_DOWN_FLOAT } |
| GEMMLowp output stage type. More... | |
| enum | ScatterFunction { Update = 0, Add = 1, Sub = 2, Max = 3, Min = 4 } |
| Scatter Function. More... | |
| enum | CLTunerMode { EXHAUSTIVE, NORMAL, RAPID } |
| < OpenCL tuner modes More... | |
| enum | CLGEMMKernelType { NATIVE, RESHAPED, RESHAPED_ONLY_RHS, RESHAPED_ONLY_RHS_MMUL } |
| OpenCL GEMM kernel types. More... | |
| enum | CLBackendType { Native, Clvk } |
| List the possible OpenCL backends. More... | |
| enum | FFTDirection { Forward, Inverse } |
| FFT direction to use. More... | |
| enum | MappingType { BLOBS, OFFSETS } |
| Mapping type. More... | |
| enum | StatusCode { Success = AclSuccess, RuntimeError = AclRuntimeError, OutOfMemory = AclOutOfMemory, Unimplemented = AclUnimplemented, UnsupportedTarget = AclUnsupportedTarget, InvalidTarget = AclInvalidTarget, InvalidArgument = AclInvalidArgument, UnsupportedConfig = AclUnsupportedConfig, InvalidObjectState = AclInvalidObjectState } |
| enum | Target { Cpu = AclTarget::AclCpu, GpuOcl = AclTarget::AclGpuOcl } |
| enum | ExecutionMode { FastRerun = AclPreferFastRerun, FastStart = AclPreferFastStart } |
| enum | ImportMemoryType { HostPtr = AclImportMemoryType::AclHostPtr } |
| enum | CLImage2DType { ReadOnly, WriteOnly } |
| OpenCL Image2D types. More... | |
| enum | LogicalOperation { Unknown, And, Or, Not } |
| List of supported logical operations. More... | |
Functions | |
| std::string | get_cl_type_from_data_type (const DataType &dt) |
| Translates a tensor data type to the appropriate OpenCL type. More... | |
| std::string | get_cl_promoted_type_from_data_type (const DataType &dt) |
| Translates a tensor data type to the appropriate OpenCL promoted type. More... | |
| std::string | get_cl_unsigned_type_from_element_size (size_t element_size) |
| Translates the element size to an unsigned integer data type. More... | |
| std::string | get_cl_signed_type_from_element_size (size_t element_size) |
| Translates the element size to an signed integer data type. More... | |
| std::string | get_cl_select_type_from_data_type (const DataType &dt) |
| Translates a tensor data type to the appropriate OpenCL select type. More... | |
| std::string | get_cl_dot8_acc_type_from_data_type (const DataType &dt) |
| Translates a tensor data type to the appropriate OpenCL dot8 accumulator type. More... | |
| std::string | get_data_size_from_data_type (const DataType &dt) |
| Get the size of a data type in number of bits. More... | |
| GPUTarget | get_target_from_device (const cl::Device &device) |
| Helper function to get the GPU target from CL device. More... | |
| CLVersion | get_cl_version (const cl::Device &device) |
| Helper function to get the highest OpenCL version supported. More... | |
| size_t | get_cl_image_pitch_alignment (const cl::Device &device) |
| Helper function to get the cl_image pitch alignment in pixels. More... | |
| bool | get_cl_non_uniform_work_group_supported (const cl::Device &device) |
| Helper function to check whether non-uniform work group is supported. More... | |
| bool | device_supports_extension (const cl::Device &device, const char *extension_name) |
| Helper function to check whether a given extension is supported. More... | |
| bool | fp16_supported (const cl::Device &device) |
| Helper function to check whether the cl_khr_fp16 extension is supported. More... | |
| bool | arm_non_uniform_workgroup_supported (const cl::Device &device) |
| Helper function to check whether the arm_non_uniform_work_group_size extension is supported. More... | |
| bool | dot8_supported (const cl::Device &device) |
| Helper function to check whether the cl_arm_integer_dot_product_int8 extension is supported. More... | |
| bool | dot8_acc_supported (const cl::Device &device) |
| Helper function to check whether the cl_arm_integer_dot_product_accumulate_int8 extension is supported. More... | |
| bool | cl_winograd_convolution_layer_supported (const Size2D &output_tile, const Size2D &kernel_size, DataLayout data_layout) |
| This function checks if the Winograd configuration (defined through the output tile, kernel size and the data layout) is supported on OpenCL. More... | |
| size_t | preferred_vector_width (const cl::Device &device, DataType dt) |
| Helper function to get the preferred native vector width size for built-in scalar types that can be put into vectors. More... | |
| bool | preferred_dummy_work_items_support (const cl::Device &device) |
| Helper function to check if "dummy work-items" are preferred to have a power of two NDRange In case dummy work-items is enabled, it is OpenCL kernel responsibility to check if the work-item is out-of range or not. More... | |
| bool | image2d_from_buffer_supported (const cl::Device &device) |
| Helper function to check whether the cl_khr_image2d_from_buffer extension is supported. More... | |
| 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. More... | |
| cl::NDRange | create_lws_hint_parallel_implementations (unsigned int input_dimension, unsigned int vector_size) |
| Creates a suitable LWS hint object for parallel implementations. More... | |
| bool | get_wbsm_support_info (const cl::Device &device) |
| void | set_wbsm (cl::Kernel &kernel, cl_int wbsm_hint) |
| bool | export_to_cl_image (const ITensorInfo *tensor) |
| void | set_unroll_with_pragma (CLBuildOptions &built_opts, std::initializer_list< int > values) |
| bool | arm_matrix_multiply_supported (const cl::Device &device) |
| Helper function to check whether the cl_arm_matrix_multiply extension is supported. More... | |
| bool | command_buffer_supported (const cl::Device &device) |
| Check whether cl_khr_command_buffer extension is supported by the specified CL device. More... | |
| bool | command_buffer_mutable_dispatch_supported (const cl::Device &device) |
| Check whether cl_khr_command_buffer_mutable_dispatch extension is supported by the specified CL device. More... | |
| bool | opencl_is_available () |
| Check if OpenCL is available. More... | |
| template<typename T > | |
| bool | operator== (const Dimensions< T > &lhs, const Dimensions< T > &rhs) |
| Check that given dimensions are equal. More... | |
| template<typename T > | |
| bool | operator!= (const Dimensions< T > &lhs, const Dimensions< T > &rhs) |
| Check that given dimensions are not equal. More... | |
| template<typename... T> | |
| void | ignore_unused (T &&...) |
| Ignores unused arguments. More... | |
| Status | create_error (ErrorCode error_code, std::string msg) |
| Creates an error containing the error message. More... | |
| Status | create_error_msg (ErrorCode error_code, const char *func, const char *file, int line, const char *msg) |
| Creates an error and the error message. More... | |
| void | throw_error (Status err) |
| Throw an std::runtime_error. More... | |
| const std::string & | string_from_target (GPUTarget target) |
| Translates a given gpu device target to string. More... | |
| GPUTarget | get_target_from_name (const std::string &device_name) |
| Helper function to get the GPU target from a device name. More... | |
| GPUTarget | get_arch_from_target (GPUTarget target) |
| Helper function to get the GPU arch. More... | |
| template<typename... Args> | |
| bool | gpu_target_is_in (GPUTarget target_to_check, GPUTarget target, Args... targets) |
| Helper function to check whether a gpu target is equal to the provided targets. More... | |
| bool | gpu_target_is_in (GPUTarget target_to_check, GPUTarget target) |
| Variant of gpu_target_is_in for comparing two targets. More... | |
| template<typename L , typename... Ts> | |
| void | execute_window_loop (const Window &w, L &&lambda_function, Ts &&...iterators) |
| Iterate through the passed window, automatically adjusting the iterators and calling the lambda_functino for each element. More... | |
| template<typename T > | |
| void | permute (Dimensions< T > &dimensions, const PermutationVector &perm) |
| Permutes given Dimensions according to a permutation vector. More... | |
| void | permute (TensorShape &shape, const PermutationVector &perm) |
| Permutes given TensorShape according to a permutation vector. More... | |
| ValidRegion | calculate_valid_region_scale (const ITensorInfo &src_info, const TensorShape &dst_shape, InterpolationPolicy interpolate_policy, SamplingPolicy sampling_policy, bool border_undefined) |
| Helper function to calculate the Valid Region for Scale. More... | |
| Coordinates | index2coords (const TensorShape &shape, int index) |
| Convert a linear index into n-dimensional coordinates. More... | |
| int | coords2index (const TensorShape &shape, const Coordinates &coord) |
| Convert n-dimensional coordinates into a linear index. More... | |
| const std::map< DataLayout, std::vector< DataLayoutDimension > > & | get_layout_map () |
| Returns a static map used to find an index or dimension based on a data layout. More... | |
| size_t | get_data_layout_dimension_index (const DataLayout &data_layout, const DataLayoutDimension &data_layout_dimension) |
| Get the index of the given dimension. More... | |
| DataLayoutDimension | get_index_data_layout_dimension (const DataLayout &data_layout, const size_t index) |
| Get the DataLayoutDimension of a given index and layout. More... | |
| Size2D | compute_winograd_convolution_tiles (const Size2D &in_dims, const Size2D &kernel_size, const Size2D &output_tile_size, const PadStrideInfo &conv_info) |
| Calculate the number of output tiles required by Winograd Convolution layer. More... | |
| template<typename T > | |
| T | wrap_around (T x, T m) |
| Wrap-around a number within the range 0 <= x < m. More... | |
| Coordinates & | convert_negative_axis (Coordinates &coords, int max_value) |
| Convert negative coordinates to positive in the range [0, num_dims_input]. More... | |
| int | adjust_down (int required, int available, int step) |
Decrease required in steps of step until it's less than available. More... | |
| int | adjust_up (int required, int available, int step) |
Increase required in steps of step until it's greater than available. More... | |
| bool | operator== (const QuantizationInfo &lhs, const QuantizationInfo &rhs) |
| Check whether two quantization info are equal. More... | |
| bool | operator!= (const QuantizationInfo &lhs, const QuantizationInfo &rhs) |
| Check whether two quantization info are not equal. More... | |
| bool | operator== (const UniformQuantizationInfo &lhs, const UniformQuantizationInfo &rhs) |
| Check whether two quantization info are equal. More... | |
| bool | operator!= (const UniformQuantizationInfo &lhs, const UniformQuantizationInfo &rhs) |
| Check whether two quantization info are not equal. More... | |
| template<typename INFO_TYPE > | |
| uint8_t | quantize_qasymm8 (float value, const INFO_TYPE &qinfo, RoundingPolicy rounding_policy=RoundingPolicy::TO_NEAREST_UP) |
| Quantize a value given an unsigned 8-bit asymmetric quantization scheme. More... | |
| template<typename INFO_TYPE > | |
| int8_t | quantize_qasymm8_signed (float value, const INFO_TYPE &qinfo, RoundingPolicy rounding_policy=RoundingPolicy::TO_NEAREST_UP) |
| Quantize a value given a signed 8-bit asymmetric quantization scheme. More... | |
| int8_t | quantize_qsymm8 (float value, const QuantizationInfo &qinfo) |
| Quantize a value given a 8-bit symmetric quantization scheme. More... | |
| int8_t | quantize_qsymm8_per_channel (float value, const QuantizationInfo &qinfo, size_t channel_id=0) |
| Quantize a value given a 8-bit symmetric per channel quantization scheme. More... | |
| template<typename INFO_TYPE > | |
| float | dequantize_qasymm8 (uint8_t value, const INFO_TYPE &qinfo) |
| Dequantize a value given an unsigned 8-bit asymmetric quantization scheme. More... | |
| template<typename INFO_TYPE > | |
| float | dequantize_qasymm8_signed (int8_t value, const INFO_TYPE &qinfo) |
| Dequantize a value given a signed 8-bit asymmetric quantization scheme. More... | |
| float | dequantize (uint8_t value, float scale, int32_t offset) |
| Dequantize a value given an 8-bit asymmetric quantization scheme. More... | |
| float | dequantize_qsymm8 (int8_t value, const UniformQuantizationInfo &qinfo) |
| Dequantize a value given a 8-bit symmetric quantization scheme. More... | |
| float | dequantize (int8_t value, float scale) |
| Dequantize a value given a 8-bit symmetric quantization scheme. More... | |
| float | dequantize (int16_t value, float scale) |
| Dequantize a value given a 16-bit symmetric quantization scheme. More... | |
| float | dequantize (uint16_t value, float scale, int32_t offset) |
| Dequantize a value given a 16-bit asymmetric quantization scheme. More... | |
| float | dequantize (int32_t value, float scale, int32_t offset) |
| Dequantize a value given a 32-bit asymmetric quantization scheme. More... | |
| int16_t | quantize_qsymm16 (float value, const UniformQuantizationInfo &qinfo, RoundingPolicy rounding_policy=RoundingPolicy::TO_NEAREST_UP) |
| Quantize a value given a 16-bit symmetric quantization scheme. More... | |
| float | dequantize_qsymm16 (int16_t value, const UniformQuantizationInfo &qinfo) |
| Dequantize a value given a 16-bit symmetric quantization scheme. More... | |
| int16_t | quantize_qsymm16 (float value, const QuantizationInfo &qinfo) |
| Quantize a value given a 16-bit symmetric quantization scheme. More... | |
| float | dequantize_qsymm16 (int16_t value, const QuantizationInfo &qinfo) |
| Dequantize a value given a 16-bit symmetric quantization scheme. More... | |
| uint16_t | quantize_qasymm16 (float value, const UniformQuantizationInfo &qinfo, RoundingPolicy rounding_policy=RoundingPolicy::TO_NEAREST_UP) |
| Quantize a value given a 16-bit asymmetric quantization scheme. More... | |
| float | dequantize_qasymm16 (uint16_t value, const UniformQuantizationInfo &qinfo) |
| Dequantize a value given a 16-bit asymmetric quantization scheme. More... | |
| uint16_t | quantize_qasymm16 (float value, const QuantizationInfo &qinfo) |
| Quantize a value given a 16-bit asymmetric quantization scheme. More... | |
| float | dequantize_qasymm16 (uint16_t value, const QuantizationInfo &qinfo) |
| Dequantize a value given a 16-bit asymmetric quantization scheme. More... | |
| float | dequantize_s32 (int32_t value, const UniformQuantizationInfo &qinfo) |
| Dequantize a value given a 32-bit asymmetric quantization scheme. More... | |
| float | dequantize_s32 (int32_t value, const QuantizationInfo &qinfo) |
| Dequantize a value given a 32-bit asymmetric quantization scheme. More... | |
| UniformQuantizationInfo | compute_requantization_scale_offset (const UniformQuantizationInfo &uqinfo_in, const UniformQuantizationInfo &uqinfo_out) |
| int | round (float x, RoundingPolicy rounding_policy) |
| Return a rounded value of x. More... | |
| bool | operator== (const TensorInfo &lhs, const TensorInfo &rhs) |
| Check whether two tensor info are equal. More... | |
| bool | operator== (const ValidRegion &lhs, const ValidRegion &rhs) |
| int | interleave_by (const WeightFormat wf) |
| int | block_by (const WeightFormat wf) |
| bool | is_fixed_format (const WeightFormat &wf) |
| bool | is_fixed_format_fast_math (const WeightFormat &wf) |
| const std::string & | string_from_activation_func (const ActivationFunction &act) |
| Translates a given activation function to a string. More... | |
| const std::string & | string_from_data_layout (DataLayout dl) |
| Convert a data layout identity into a string. More... | |
| size_t | data_size_from_type (DataType data_type) |
| The size in bytes of the data type. More... | |
| size_t | element_size_from_data_type (DataType dt) |
| The size in bytes of the data type. More... | |
| DataType | data_type_from_format (Format format) |
| Return the data type used by a given single-planar pixel format. More... | |
| DataType | get_promoted_data_type (DataType dt) |
| Return the promoted data type of a given data type. More... | |
| std::tuple< PixelValue, PixelValue > | get_min_max (DataType dt) |
| Compute the mininum and maximum values a data type can take. More... | |
| const std::string & | string_from_data_type (DataType dt) |
| Convert a data type identity into a string. More... | |
| DataType | data_type_from_name (const std::string &name) |
| Convert a string to DataType. More... | |
| inline ::std::istream & | operator>> (::std::istream &stream, DataType &data_type) |
| Input Stream operator for DataType. More... | |
| bool | is_data_type_float (DataType dt) |
| Check if a given data type is of floating point type. More... | |
| bool | is_data_type_quantized (DataType dt) |
| Check if a given data type is of quantized type. More... | |
| bool | is_data_type_quantized_asymmetric (DataType dt) |
| Check if a given data type is of asymmetric quantized type. More... | |
| bool | is_data_type_quantized_asymmetric_signed (DataType dt) |
| Check if a given data type is of asymmetric quantized signed type. More... | |
| bool | is_data_type_quantized_asymmetric_char (DataType dt) |
| Check if a given data type is of 8-bit asymmetric quantized signed type. More... | |
| bool | is_data_type_quantized_symmetric (DataType dt) |
| Check if a given data type is of symmetric quantized type. More... | |
| bool | is_data_type_quantized_per_channel (DataType dt) |
| Check if a given data type is of per channel type. More... | |
| template<typename T > | |
| bool | check_value_range (T val, DataType dt, QuantizationInfo qinfo=QuantizationInfo()) |
| Returns true if the value can be represented by the given data type. More... | |
| std::string | cpu_impl_dt (const DataType &data_type) |
| Returns the suffix string of CPU kernel implementation names based on the given data type. More... | |
| size_t | pixel_size_from_format (Format format) |
| The size in bytes of the pixel format. More... | |
| int | plane_idx_from_channel (Format format, Channel channel) |
| Return the plane index of a given channel given an input format. More... | |
| int | channel_idx_from_format (Format format, Channel channel) |
| Return the channel index of a given channel given an input format. More... | |
| size_t | num_planes_from_format (Format format) |
| Return the number of planes for a given format. More... | |
| size_t | num_channels_from_format (Format format) |
| Return the number of channels for a given single-planar pixel format. More... | |
| const std::string & | string_from_format (Format format) |
| Convert a tensor format into a string. More... | |
| 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's first dimension, getting rounded down to its closest valid vector size. More... | |
| const std::string & | string_from_interpolation_policy (InterpolationPolicy policy) |
| Translates a given interpolation policy to a string. More... | |
| template<typename S , typename T > | |
| constexpr auto | DIV_CEIL (S val, T m) -> decltype((val+m - 1)/m) |
| Calculate the rounded up quotient of val / m. More... | |
| template<typename S , typename T > | |
| 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. More... | |
| template<typename S , typename T > | |
| auto | floor_to_multiple (S value, T divisor) -> decltype((value/divisor) *divisor) |
| Computes the largest number smaller or equal to value that is a multiple of divisor. More... | |
| std::string | lower_string (const std::string &val) |
| Lower a given string. More... | |
| std::string | upper_string (const std::string &val) |
| Raise a given string to upper case. More... | |
| std::string | float_to_string_with_full_precision (float val) |
| Create a string with the float in full precision. More... | |
| std::string | join (const std::vector< std::string > strings, const std::string &sep) |
Join a sequence of strings with separator sep. More... | |
| std::string | read_file (const std::string &filename, bool binary) |
| Load an entire file in memory. More... | |
| template<typename T > | |
| void | permute_strides (Dimensions< T > &dimensions, const PermutationVector &perm) |
| Permutes the given dimensions according the permutation vector. More... | |
| PadStrideInfo | calculate_same_pad (TensorShape input_shape, TensorShape weights_shape, PadStrideInfo conv_info, DataLayout data_layout=DataLayout::NCHW, const Size2D &dilation=Size2D(1u, 1u), const DimensionRoundingType &rounding_type=DimensionRoundingType::FLOOR) |
| Calculate padding requirements in case of SAME padding. More... | |
| std::pair< unsigned int, unsigned int > | deconvolution_output_dimensions (unsigned int in_width, unsigned int in_height, unsigned int kernel_width, unsigned int kernel_height, const PadStrideInfo &pad_stride_info) |
| Returns expected width and height of the deconvolution's output tensor. More... | |
| std::pair< unsigned int, unsigned int > | scaled_dimensions (int width, int height, int kernel_width, int kernel_height, const PadStrideInfo &pad_stride_info, const Size2D &dilation=Size2D(1U, 1U)) |
| Returns expected width and height of output scaled tensor depending on dimensions rounding mode. More... | |
| std::pair< int, int > | scaled_dimensions_signed (int width, int height, int kernel_width, int kernel_height, const PadStrideInfo &pad_stride_info) |
| Returns calculated width and height of output scaled tensor depending on dimensions rounding mode. More... | |
| std::tuple< int, int, int > | scaled_3d_dimensions_signed (int width, int height, int depth, int kernel_width, int kernel_height, int kernel_depth, const Pooling3dLayerInfo &pool3d_info) |
| Returns calculated width, height and depth of output scaled tensor depending on dimensions rounding mode. More... | |
| bool | needs_serialized_reduction (ReductionOperation op, DataType dt, unsigned int axis) |
| Check if the given reduction operation should be handled in a serial way. More... | |
| QuantizationInfo | get_softmax_output_quantization_info (DataType input_type, bool is_log) |
| Returns output quantization information for softmax layer. More... | |
| std::pair< int32_t, int32_t > | get_quantized_activation_min_max (const ActivationLayerInfo &act_info, DataType data_type, UniformQuantizationInfo oq_info) |
| Returns a pair of minimum and maximum values for a quantized activation. More... | |
| const std::string & | string_from_channel (Channel channel) |
| Convert a channel identity into a string. More... | |
| const std::string & | string_from_border_mode (BorderMode border_mode) |
| Translates a given border mode policy to a string. More... | |
| const std::string & | string_from_norm_type (NormType type) |
| Translates a given normalization type to a string. More... | |
| const std::string & | string_from_pooling_type (PoolingType type) |
| Translates a given pooling type to a string. More... | |
| bool | is_pool_region_entirely_outside_input (const PoolingLayerInfo &info) |
| Check if the pool region is entirely outside the input tensor. More... | |
| bool | is_pool_3d_region_entirely_outside_input (const Pooling3dLayerInfo &info) |
| Check if the 3d pool region is entirely outside the input tensor. More... | |
| bool | is_symmetric (const Padding3D &info) |
| Check if the 3D padding is symmetric i.e. More... | |
| const std::string & | string_from_gemmlowp_output_stage (GEMMLowpOutputStageType output_stage) |
| Translates a given GEMMLowp output stage to a string. More... | |
| std::string | string_from_pixel_value (const PixelValue &value, const DataType data_type) |
| Convert a PixelValue to a string, represented through the specific data type. More... | |
| std::unordered_map< const ITensorInfo *, PaddingSize > | get_padding_info (std::initializer_list< const ITensorInfo * > infos) |
| Stores padding information before configuring a kernel. More... | |
| std::unordered_map< const ITensorInfo *, PaddingSize > | get_padding_info (std::initializer_list< const ITensor * > tensors) |
| Stores padding information before configuring a kernel. More... | |
| 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. More... | |
| size_t | num_of_elements_in_range (const float start, const float end, const float step) |
| Returns the number of elements required to go from start to end with the wanted step. More... | |
| template<typename... Ts> | |
| arm_compute::Status | error_on_nullptr (const char *function, const char *file, const int line, Ts &&...pointers) |
| Create an error if one of the pointers is a nullptr. More... | |
| arm_compute::Status | error_on_mismatching_windows (const char *function, const char *file, const int line, const Window &full, const Window &win) |
| Return an error if the passed window is invalid. More... | |
| arm_compute::Status | error_on_invalid_subwindow (const char *function, const char *file, const int line, const Window &full, const Window &sub) |
| Return an error if the passed subwindow is invalid. More... | |
| arm_compute::Status | error_on_window_not_collapsable_at_dimension (const char *function, const char *file, const int line, const Window &full, const Window &window, const int dim) |
| Return an error if the window can't be collapsed at the given dimension. More... | |
| arm_compute::Status | error_on_coordinates_dimensions_gte (const char *function, const char *file, const int line, const Coordinates &pos, unsigned int max_dim) |
| Return an error if the passed coordinates have too many dimensions. More... | |
| arm_compute::Status | error_on_window_dimensions_gte (const char *function, const char *file, const int line, const Window &win, unsigned int max_dim) |
| Return an error if the passed window has too many dimensions. More... | |
| template<typename T , typename... Ts> | |
| arm_compute::Status | error_on_mismatching_dimensions (const char *function, const char *file, int line, const Dimensions< T > &dim1, const Dimensions< T > &dim2, Ts &&...dims) |
| Return an error if the passed dimension objects differ. More... | |
| bool | has_format_horizontal_subsampling (Format format) |
| Return true if the given format has horizontal subsampling. More... | |
| bool | has_format_vertical_subsampling (Format format) |
| Return true if the given format has vertical subsampling. More... | |
| TensorShape | adjust_odd_shape (const TensorShape &shape, Format format) |
| Adjust tensor shape size if width or height are odd for a given multi-planar format. More... | |
| template<typename... Ts> | |
| arm_compute::Status | error_on_tensors_not_even (const char *function, const char *file, int line, const Format &format, const ITensor *tensor1, Ts... tensors) |
| Return an error if the passed tensor objects are not even. More... | |
| TensorShape | calculate_subsampled_shape (const TensorShape &shape, Format format, Channel channel=Channel::UNKNOWN) |
| Calculate subsampled shape for a given format and channel. More... | |
| template<typename... Ts> | |
| arm_compute::Status | error_on_tensors_not_subsampled (const char *function, const char *file, int line, const Format &format, const TensorShape &shape, const ITensor *tensor1, Ts... tensors) |
| Return an error if the passed tensor objects are not sub-sampled. More... | |
| template<typename... Ts> | |
| arm_compute::Status | error_on_mismatching_shapes (const char *function, const char *file, const int line, const ITensorInfo *tensor_info_1, const ITensorInfo *tensor_info_2, Ts... tensor_infos) |
| Return an error if the passed two tensor infos have different shapes from the given dimension. More... | |
| template<typename... Ts> | |
| arm_compute::Status | error_on_mismatching_shapes (const char *function, const char *file, const int line, const ITensor *tensor_1, const ITensor *tensor_2, Ts... tensors) |
| Return an error if the passed two tensors have different shapes from the given dimension. More... | |
| template<typename... Ts> | |
| arm_compute::Status | error_on_mismatching_shapes (const char *function, const char *file, const int line, unsigned int upper_dim, const ITensorInfo *tensor_info_1, const ITensorInfo *tensor_info_2, Ts... tensor_infos) |
| Return an error if the passed two tensors have different shapes from the given dimension. More... | |
| template<typename... Ts> | |
| arm_compute::Status | error_on_mismatching_shapes (const char *function, const char *file, const int line, unsigned int upper_dim, const ITensor *tensor_1, const ITensor *tensor_2, Ts... tensors) |
| Return an error if the passed two tensors have different shapes from the given dimension. More... | |
| template<typename... Ts> | |
| arm_compute::Status | error_on_mismatching_data_layouts (const char *function, const char *file, const int line, const ITensorInfo *tensor_info, Ts... tensor_infos) |
| Return an error if the passed tensor infos have different data layouts. More... | |
| template<typename... Ts> | |
| arm_compute::Status | error_on_mismatching_data_layouts (const char *function, const char *file, const int line, const ITensor *tensor, Ts... tensors) |
| Return an error if the passed tensors have different data layouts. More... | |
| template<typename... Ts> | |
| arm_compute::Status | error_on_mismatching_data_types (const char *function, const char *file, const int line, const ITensorInfo *tensor_info, Ts... tensor_infos) |
| Return an error if the passed two tensor infos have different data types. More... | |
| template<typename... Ts> | |
| arm_compute::Status | error_on_mismatching_data_types (const char *function, const char *file, const int line, const ITensor *tensor, Ts... tensors) |
| Return an error if the passed two tensors have different data types. More... | |
| template<typename... Ts> | |
| arm_compute::Status | error_on_mismatching_quantization_info (const char *function, const char *file, const int line, const ITensorInfo *tensor_info_1, const ITensorInfo *tensor_info_2, Ts... tensor_infos) |
| Return an error if the passed tensor infos have different asymmetric quantized data types or different quantization info. More... | |
| template<typename... Ts> | |
| arm_compute::Status | error_on_mismatching_quantization_info (const char *function, const char *file, const int line, const ITensor *tensor_1, const ITensor *tensor_2, Ts... tensors) |
| Return an error if the passed tensor have different asymmetric quantized data types or different quantization info. More... | |
| template<typename T , typename F , typename... Fs> | |
| void | error_on_format_not_in (const char *function, const char *file, const int line, const T *object, F &&format, Fs &&...formats) |
| Throw an error if the format of the passed tensor/multi-image does not match any of the formats provided. More... | |
| template<typename T , typename... Ts> | |
| arm_compute::Status | error_on_data_type_not_in (const char *function, const char *file, const int line, const ITensorInfo *tensor_info, T &&dt, Ts &&...dts) |
| Return an error if the data type of the passed tensor info does not match any of the data types provided. More... | |
| template<typename T , typename... Ts> | |
| arm_compute::Status | error_on_data_type_not_in (const char *function, const char *file, const int line, const ITensor *tensor, T &&dt, Ts &&...dts) |
| Return an error if the data type of the passed tensor does not match any of the data types provided. More... | |
| template<typename T , typename... Ts> | |
| arm_compute::Status | error_on_data_layout_not_in (const char *function, const char *file, const int line, const ITensorInfo *tensor_info, T &&dl, Ts &&...dls) |
| Return an error if the data layout of the passed tensor info does not match any of the data layouts provided. More... | |
| template<typename T , typename... Ts> | |
| arm_compute::Status | error_on_data_layout_not_in (const char *function, const char *file, const int line, const ITensor *tensor, T &&dl, Ts &&...dls) |
| Return an error if the data layout of the passed tensor does not match any of the data layout provided. More... | |
| template<typename T , typename... Ts> | |
| arm_compute::Status | error_on_data_type_channel_not_in (const char *function, const char *file, const int line, const ITensorInfo *tensor_info, size_t num_channels, T &&dt, Ts &&...dts) |
| Return an error if the data type or the number of channels of the passed tensor info does not match any of the data types and number of channels provided. More... | |
| template<typename T , typename... Ts> | |
| arm_compute::Status | error_on_data_type_channel_not_in (const char *function, const char *file, const int line, const ITensor *tensor, size_t num_channels, T &&dt, Ts &&...dts) |
| Return an error if the data type or the number of channels of the passed tensor does not match any of the data types and number of channels provided. More... | |
| arm_compute::Status | error_on_unsupported_fp16 (const char *function, const char *file, const int line, const ITensorInfo *tensor_info, bool is_fp16_supported) |
| Return an error if the data type of the passed tensor info is FP16 and FP16 extension is not supported by the device. More... | |
| arm_compute::Status | error_on_unsupported_fp16 (const char *function, const char *file, const int line, const ITensor *tensor, bool is_fp16_supported) |
| Return an error if the data type of the passed tensor is FP16 and FP16 extension is not supported by the device. More... | |
| arm_compute::Status | error_on_tensor_not_2d (const char *function, const char *file, const int line, const ITensor *tensor) |
| Return an error if the tensor is not 2D. More... | |
| arm_compute::Status | error_on_tensor_not_2d (const char *function, const char *file, const int line, const ITensorInfo *tensor) |
| Return an error if the tensor info is not 2D. More... | |
| template<typename T , typename... Ts> | |
| arm_compute::Status | error_on_channel_not_in (const char *function, const char *file, const int line, T cn, T &&channel, Ts &&...channels) |
| Return an error if the channel is not in channels. More... | |
| arm_compute::Status | error_on_channel_not_in_known_format (const char *function, const char *file, const int line, Format fmt, Channel cn) |
| Return an error if the channel is not in format. More... | |
| arm_compute::Status | error_on_unconfigured_kernel (const char *function, const char *file, const int line, const IKernel *kernel) |
| Return an error if the kernel is not configured. More... | |
| arm_compute::Status | error_on_invalid_subtensor (const char *function, const char *file, const int line, const TensorShape &parent_shape, const Coordinates &coords, const TensorShape &shape) |
| Return an error if if the coordinates and shape of the subtensor are within the parent tensor. More... | |
| arm_compute::Status | error_on_invalid_subtensor_valid_region (const char *function, const char *file, const int line, const ValidRegion &parent_valid_region, const ValidRegion &valid_region) |
| Return an error if the valid region of a subtensor is not inside the valid region of the parent tensor. More... | |
| std::string | build_information () |
| Returns the arm_compute library build information. More... | |
| void | swap (Window &lhs, Window &rhs) |
| bool | operator== (const Window &lhs, const Window &rhs) |
| Coordinates | convert_window_coord_to_position (const Window &w, const Coordinates &offset) |
| Convert an offset in window steps into absolute coordinates. More... | |
| template<typename L > | |
| WindowIterator< L > | create_window_iterator (const Window &w, const Coordinates &start, const Coordinates &end, L &&lambda_function) |
| Create a WindowIterator object. More... | |
| arm_compute::DataLayout | data_layout_from_name (const std::string &name) |
| Converts a string to a strong types enumeration DataLayout. More... | |
| inline ::std::istream & | operator>> (::std::istream &stream, arm_compute::DataLayout &data_layout) |
| Input Stream operator for DataLayout. More... | |
| std::tuple< cl::Context, cl::Device, cl_int > | create_opencl_context_and_device (CLBackendType cl_backend_type) |
| This function creates an OpenCL context and a device. More... | |
| void | schedule_kernel_on_ctx (CLRuntimeContext *ctx, ICLKernel *kernel, bool flush=true) |
| Schedules a kernel using the context if not nullptr else uses the legacy scheduling flow. More... | |
| cl::Platform | select_preferable_platform (CLBackendType cl_backend_type) |
| This function selects the OpenCL platform based on the backend type. More... | |
| CLTunerMode | tuner_mode_from_name (const std::string &name) |
| Converts a string to a strong types enumeration CLTunerMode. More... | |
| inline ::std::istream & | operator>> (::std::istream &stream, CLTunerMode &tuner_mode) |
| Input Stream operator for CLTunerMode. More... | |
| void | save_program_cache_to_file (const std::string &filename="cache.bin") |
| This function saves opencl kernels library to a file. More... | |
| void | restore_program_cache_from_file (const std::string &filename="cache.bin") |
| This function loads prebuilt opencl kernels from a file. More... | |
| IContext * | get_internal (AclContext ctx) |
| Extract internal representation of a Context. More... | |
| IOperator * | get_internal (AclOperator op) |
| Extract internal representation of an Operator. More... | |
| IQueue * | get_internal (AclQueue queue) |
| Extract internal representation of a Queue. More... | |
| ITensorV2 * | get_internal (AclTensor tensor) |
| Extract internal representation of a Tensor. More... | |
| TensorPack * | get_internal (AclTensorPack pack) |
| Extract internal representation of a TensoPack. More... | |
| cl::Image2D | create_image2d_from_tensor (const ICLTensor *tensor, CLImage2DType image_type) |
| Create a cl::Image2D object from a tensor. More... | |
| cl::Image2D | create_image2d_from_buffer (const cl::Context &ctx, const cl::Buffer &buffer, const TensorShape &shape2d, DataType data_type, size_t image_row_pitch, CLImage2DType image_type) |
| Create a cl::Image2D object from an OpenCL buffer. More... | |
| void | handle_cl_error (const std::string &function_name, cl_int error_code) |
| Check for CL error code and throw exception accordingly. More... | |
| arm_compute::Status | error_on_unsupported_int64_base_atomics (const char *function, const char *file, const int line) |
| Return an error if int64_base_atomics extension is not supported by the device. More... | |
| cl::NDRange | get_default_lws_for_type (CLKernelType kernel_type, cl::NDRange gws) |
| void | enqueue (cl::CommandQueue &queue, ICLKernel &kernel, const Window &window, const cl::NDRange &lws_hint=CLKernelLibrary::get().default_ndrange(), bool use_dummy_work_items=false) |
| Add the kernel to the command queue with the given window. More... | |
| Status | error_on_unsupported_cpu_fp16 (const char *function, const char *file, const int line, const ITensorInfo *tensor_info) |
| Return an error if the data type of the passed tensor info is FP16 and FP16 support is not compiled in. More... | |
| Status | error_on_unsupported_cpu_bf16 (const char *function, const char *file, const int line, const ITensorInfo *tensor_info) |
| Return an error if the data type of the passed tensor info is BFLOAT16 and BFLOAT16 support is not compiled in. More... | |
| Status | error_on_unsupported_cpu_fp16 (const char *function, const char *file, const int line, const ITensor *tensor) |
| Return an error if the data type of the passed tensor is FP16 and FP16 support is not compiled in. More... | |
| Status | error_on_unsupported_cpu_bf16 (const char *function, const char *file, const int line, const ITensor *tensor) |
| Return an error if the data type of the passed tensor is BFLOAT16 and BFLOAT16 support is not compiled in. More... | |
| bool | auto_init_if_empty (ITensorInfo &info, const TensorShape &shape, int num_channels, DataType data_type, QuantizationInfo quantization_info=QuantizationInfo()) |
| Auto initialize the tensor info (shape, number of channels and data type) if the current assignment is empty. More... | |
| bool | auto_init_if_empty (ITensorInfo &info_sink, const ITensorInfo &info_source) |
| Auto initialize the tensor info using another tensor info. More... | |
| bool | set_shape_if_empty (ITensorInfo &info, const TensorShape &shape) |
| Set the shape to the specified value if the current assignment is empty. More... | |
| bool | set_format_if_unknown (ITensorInfo &info, Format format) |
| Set the format, data type and number of channels to the specified value if the current data type is unknown. More... | |
| bool | set_data_type_if_unknown (ITensorInfo &info, DataType data_type) |
| Set the data type and number of channels to the specified value if the current data type is unknown. More... | |
| bool | set_data_layout_if_unknown (ITensorInfo &info, DataLayout data_layout) |
| Set the data layout to the specified value if the current data layout is unknown. More... | |
| bool | set_quantization_info_if_empty (ITensorInfo &info, QuantizationInfo quantization_info) |
| Set the quantization info to the specified value if the current quantization info is empty and the data type of asymmetric quantized type. More... | |
| int | offset_int_vec (int offset) |
| template<typename TensorType > | |
| WorkspaceData< TensorType > | manage_workspace (const experimental::MemoryRequirements &mem_reqs, MemoryGroup &mgroup, ITensorPack &run_pack) |
| template<typename TensorType > | |
| WorkspaceData< TensorType > | manage_workspace (const experimental::MemoryRequirements &mem_reqs, MemoryGroup &mgroup, ITensorPack &run_pack, ITensorPack &prep_pack) |
| template<typename TensorType > | |
| void | release_prepare_tensors (WorkspaceData< TensorType > &workspace, ITensorPack &prep_pack) |
| template<typename TensorType > | |
| void | release_temporaries (const experimental::MemoryRequirements &mem_reqs, WorkspaceData< TensorType > &workspace) |
| Utility function to release tensors with lifetime marked as Prepare. More... | |
| unsigned int | get_normalization_dimension_index (DataLayout layout, const NormalizationLayerInfo &info) |
| Calculate the normalization dimension index for a given normalization type. More... | |
| bool | has_holes (const ITensorInfo &info) |
| Check if the tensor has any holes. More... | |
| bool | has_holes (const ITensorInfo &info, size_t dimension) |
| Check if the tensor has any holes. More... | |
| template<typename T , typename... Ts> | |
| Strides | compute_strides (const ITensorInfo &info, T stride_x, Ts &&...fixed_strides) |
| Create a strides object based on the provided strides and the tensor dimensions. More... | |
| template<typename... Ts> | |
| Strides | compute_strides (const ITensorInfo &info) |
| Create a strides object based on the tensor dimensions. More... | |
| unsigned int | get_next_power_two (unsigned int x) |
| Given an integer value, this function returns the next power of two. More... | |
| Window | calculate_max_window (const ValidRegion &valid_region, const Steps &steps, bool skip_border, BorderSize border_size) |
| Window | calculate_max_window (const TensorShape &shape, const Steps &steps, bool skip_border, BorderSize border_size) |
| Window | calculate_max_enlarged_window (const ValidRegion &valid_region, const Steps &steps, BorderSize border_size) |
| Window | calculate_max_window_horizontal (const ValidRegion &valid_region, const Steps &steps, bool skip_border, BorderSize border_size) |
| std::pair< Window, size_t > | calculate_squashed_or_max_window (const ITensorInfo &src0, const ITensorInfo &src1) |
| std::pair< Window, size_t > | calculate_squashed_or_max_window (const ITensorInfo &src) |
| template<typename... Ts> | |
| bool | update_window_and_padding (Window &win, Ts &&...patterns) |
| Update window and padding size for each of the access patterns. More... | |
| template<typename... Ts> | |
| ValidRegion | intersect_valid_regions (const Ts &...regions) |
| Intersect multiple valid regions. More... | |
| void | colorconvert_rgb_to_rgbx (const void *__restrict input, void *__restrict output, const Window &win) |
| Convert RGB to RGBX. More... | |
| void | colorconvert_rgb_to_u8 (const void *__restrict input, void *__restrict output, const Window &win) |
| Convert RGB to U8. More... | |
| void | colorconvert_rgbx_to_rgb (const void *input, void *output, const Window &win) |
| Convert RGBX to RGB. More... | |
| template<bool yuyv, bool alpha> | |
| void | colorconvert_yuyv_to_rgb (const void *__restrict input, void *__restrict output, const Window &win) |
| Convert YUYV to RGB. More... | |
| template<bool uv, bool alpha> | |
| void | colorconvert_nv12_to_rgb (const void *__restrict input, void *__restrict output, const Window &win) |
| Convert NV12 to RGB. More... | |
| template<bool alpha> | |
| void | colorconvert_iyuv_to_rgb (const void *__restrict input, void *__restrict output, const Window &win) |
| Convert IYUV to RGB. More... | |
| template<bool yuyv> | |
| void | colorconvert_yuyv_to_nv12 (const void *__restrict input, void *__restrict output, const Window &win) |
| Convert YUYV to NV12. More... | |
| void | colorconvert_iyuv_to_nv12 (const void *__restrict input, void *__restrict output, const Window &win) |
| Convert IYUV to NV12. More... | |
| template<bool uv> | |
| void | colorconvert_nv12_to_iyuv (const void *__restrict input, void *__restrict output, const Window &win) |
| Convert NV12 to IYUV. More... | |
| template<bool yuyv> | |
| void | colorconvert_yuyv_to_iyuv (const void *__restrict input, void *__restrict output, const Window &win) |
| Convert YUYV to IYUV. More... | |
| template<bool uv> | |
| void | colorconvert_nv12_to_yuv4 (const void *__restrict input, void *__restrict output, const Window &win) |
| Convert NV12 to YUV4. More... | |
| void | colorconvert_iyuv_to_yuv4 (const void *__restrict input, void *__restrict output, const Window &win) |
| Convert IYUV to YUV4. More... | |
| template<bool alpha> | |
| void | colorconvert_rgb_to_nv12 (const void *__restrict input, void *__restrict output, const Window &win) |
| Convert RGB to NV12. More... | |
| template<bool alpha> | |
| void | colorconvert_rgb_to_iyuv (const void *__restrict input, void *__restrict output, const Window &win) |
| Convert RGB to IYUV. More... | |
| template<bool alpha> | |
| void | colorconvert_rgb_to_yuv4 (const void *__restrict input, void *__restrict output, const Window &win) |
| Convert RGB to YUV4. More... | |
| template<typename T > | |
| void | run_reverse (const Window &window, const ITensor *input, const ITensor *axis, ITensor *output, bool use_inverted_axis) |
| template<RoundingPolicy round_policy = RoundingPolicy::TO_ZERO> | |
| qasymm8x16_t | vmlaq_qasymm8 (qasymm8x16_t vd, float32x4_t vs, float32x4_t vo) |
| Perform a multiply-accumulate on all 16 components of a QASYMM8 vector. More... | |
| template<RoundingPolicy round_policy = RoundingPolicy::TO_ZERO> | |
| qasymm8x16_signed_t | vmlaq_qasymm8_signed (qasymm8x16_signed_t vd, float32x4_t vs, float32x4_t vo) |
| Perform a multiply-accumulate on all 16 components of a QASYMM8_SIGNED vector. More... | |
| uint8x16_t | finalize_quantization (int32x4x4_t &in_s32, int result_fixedpoint_multiplier, int32_t result_shift, int32x4_t result_offset_after_shift_s32, uint8x16_t min_u8, uint8x16_t max_u8, bool is_bounded_relu) |
| Performs final quantization step on 16 elements. More... | |
| int8x16_t | finalize_quantization (int32x4x4_t &in_s32, int result_fixedpoint_multiplier, int32_t result_shift, int32x4_t result_offset_after_shift_s32, int8x16_t min_s8, int8x16_t max_s8, bool is_bounded_relu) |
| Performs final quantization step on 16 elements. More... | |
| int8x16_t | finalize_quantization_symm (int32x4x4_t &in_s32, const int32x4x4_t &result_fixedpoint_multiplier, const int32x4x4_t &result_shift, const int32x4_t &result_offset_after_shift_s32, const int8x16_t &min_s8, const int8x16_t &max_s8, const bool is_bounded_relu) |
| Performs final quantization step on 16 elements for symmetric quantization. More... | |
| uint8_t | finalize_quantization (int32_t in_value, int result_fixedpoint_multiplier, int32_t result_shift, int32_t result_offset_after_shift_s32, uint8_t min_u8, uint8_t max_u8, bool is_bounded_relu) |
| Performs final quantization step on single element. More... | |
| int8_t | finalize_quantization (int32_t in_value, int result_fixedpoint_multiplier, int32_t result_shift, int32_t result_offset_after_shift_s32, int8_t min_s8, int8_t max_s8, bool is_bounded_relu) |
| Performs final quantization step on single element. More... | |
| float32x4x2_t | vdequantize (const uint8x8_t &qv, const UniformQuantizationInfo &qi) |
| Dequantize a neon vector holding 8 quantized values. More... | |
| float32x4x2_t | vdequantize (const int8x8_t &qv, const UniformQuantizationInfo &qi) |
| Dequantize a neon vector holding 8 singed quantized values. More... | |
| float32x4x4_t | vdequantize (const uint8x16_t &qv, const UniformQuantizationInfo &qi) |
| Dequantize a neon vector holding 16 quantized values. More... | |
| float32x4x4_t | vdequantize (const int8x16_t &qv, const UniformQuantizationInfo &qi) |
| Dequantize a neon vector holding 16 signed quantized values. More... | |
| float32x4x4_t | vdequantize (const uint8x16_t &qv, float scale, int32_t offset) |
| Dequantize following an asymmetric quantization scheme a neon vector holding 16 quantized values. More... | |
| float32x4x4_t | vdequantize (const int8x16_t &qv, float scale, int32_t offset) |
| Dequantize a vector of 16 values stored as signed asymmetric. More... | |
| float32x4x4_t | vdequantize (const int8x16_t &qv, const float32x4x4_t vscale) |
| Dequantize following symmetric quantization scheme a neon vector holding 16 quantized values. More... | |
| float32x4x4_t | vdequantize (const int8x16_t &qv, float scale) |
| Dequantize following a symmetric quantization scheme a neon vector holding 16 quantized values. More... | |
| uint8x8_t | vquantize (const float32x4x2_t &qv, const UniformQuantizationInfo &qi) |
| Quantize a neon vector holding 8 floating point values. More... | |
| int8x8_t | vquantize_signed (const float32x4x2_t &qv, const UniformQuantizationInfo &qi) |
| Quantize a neon vector holding 8 floating point values. More... | |
| int32x4x4_t | vquantize_internal (const float32x4x4_t &qv, float scale, int32_t offset) |
| uint8x16_t | vquantize (const float32x4x4_t &qv, const UniformQuantizationInfo &qi) |
| Quantize a neon vector holding 16 floating point values. More... | |
| int8x16_t | vquantize_signed (const float32x4x4_t &qv, const UniformQuantizationInfo &qi) |
| Signed quantize a neon vector holding 16 floating point values. More... | |
| uint16x8x2_t | vquantize_qasymm16 (const float32x4x4_t &qv, const UniformQuantizationInfo &qi) |
| Quantize to QASYMM16 a neon vector holding 16 floating point values. More... | |
| float32x4x2_t | vmax2q_f32 (float32x4x2_t a, float32x4x2_t b) |
| Compute lane-by-lane maximum between elements of a float vector with 4x2 elements. More... | |
| float32x4_t | vfloorq_f32 (float32x4_t val) |
| Calculate floor of a vector. More... | |
| float32x4_t | vroundq_rte_f32 (float32x4_t val) |
| Calculate round value of a vector to nearest with ties to even. More... | |
| float32x2_t | vinvsqrt_f32 (float32x2_t x) |
| Calculate inverse square root. More... | |
| float32x4_t | vinvsqrtq_f32 (float32x4_t x) |
| Calculate inverse square root. More... | |
| float32x2_t | vinv_f32 (float32x2_t x) |
| Calculate reciprocal. More... | |
| float32x4_t | vinvq_f32 (float32x4_t x) |
| Calculate reciprocal. More... | |
| float32x4_t | vtaylor_polyq_f32 (float32x4_t x, const std::array< float32x4_t, 8 > &coeffs) |
| Perform a 7th degree polynomial approximation using Estrin's method. More... | |
| float32x4_t | vexpq_f32 (float32x4_t x) |
| Calculate exponential. More... | |
| float32x4_t | verfq_f32 (float32x4_t x) |
| Calculate error function. More... | |
| float32x4_t | vlogq_f32 (float32x4_t x) |
| Calculate logarithm. More... | |
| float32x4_t | vtanhq_f32 (float32x4_t val) |
| Calculate hyperbolic tangent. More... | |
| float32x4_t | vpowq_f32 (float32x4_t val, float32x4_t n) |
| Calculate n power of a number. More... | |
| int32x4_t | rounding_divide_by_pow2 (int32x4_t x, int32x4_t exponent) |
| Round to the nearest division by a power-of-two using exponent. More... | |
| int32x4_t | rounding_divide_by_pow2 (int32x4_t x, int exponent) |
| Round to the nearest division by a power-of-two using exponent. More... | |
| int32_t | rounding_divide_by_pow2 (int32_t x, int exponent) |
| Round to the nearest division by a power-of-two using exponent. More... | |
| float32x4x4_t | convert_uint8x16_to_float32x4x4 (const uint8x16_t &in) |
| Converts from uint8x16 to float32x4x4_t. More... | |
| float32x4x4_t | convert_int8x16_to_float32x4x4 (const int8x16_t &in) |
| Converts from int8x16 to float32x4x4_t. More... | |
| template<typename T > | |
| float32x4x4_t | convert_to_float32x4x4 (const T &in) |
| Converts to float32x4x4_t from the specified templated 16 elements vectors. More... | |
| void | convert_float32x4x3_to_uint8x8x3 (const float32x4x3_t &in1, const float32x4x3_t &in2, uint8x8x3_t &out) |
| Converts from two float32x4x3_t to just one uint8x8x3_t. More... | |
| void | convert_float32x4x4_to_uint8x16 (const float32x4x4_t &in, uint8x16_t &out) |
| Converts from two float32x4x4_t to just one uint8x16_t. More... | |
| void | convert_float32x4x4_to_int8x16 (const float32x4x4_t &in, int8x16_t &out) |
| Converts from float32x4x4_t to just one int8x16_t. More... | |
| template<typename float_vec_type , typename int_vec_type > | |
| int_vec_type | convert_float_to_int (const float_vec_type &in) |
| Converts from float vector to integer vector. More... | |
| template<typename float_vec_type , typename int_vec_type > | |
| float_vec_type | convert_int_to_float (const int_vec_type &in) |
| Converts from integer vector to float vector. More... | |
| float32x4_t | vsinq_f32 (float32x4_t val) |
| Calculate sine. More... | |
| float32x2_t | vsin_f32 (float32x2_t val) |
| Calculate sine. More... | |
| float | vreduce (const float32x4_t &v) |
| Reduce a vector to be a scalar by accumulating all lanes in the vector. More... | |
| template<> | |
| float32x4x4_t | convert_to_float32x4x4 (const uint8x16_t &in) |
| template<> | |
| float32x4x4_t | convert_to_float32x4x4 (const int8x16_t &in) |
| template<> | |
| uint8x16_t | convert_float_to_int< float32x4x4_t, uint8x16_t > (const float32x4x4_t &in) |
| template<> | |
| float32x4x4_t | convert_int_to_float< float32x4x4_t, uint8x16_t > (const uint8x16_t &in) |
| template<> | |
| int8x16_t | convert_float_to_int< float32x4x4_t, int8x16_t > (const float32x4x4_t &in) |
| template<> | |
| float32x4x4_t | convert_int_to_float< float32x4x4_t, int8x16_t > (const int8x16_t &in) |
| template<bool is_bounded_relu> | |
| int16x8_t | finalize_quantization_int16 (int32x4x2_t &in_s32, int result_fixedpoint_multiplier, int32_t result_shift, int16x8_t min_s16, int16x8_t max_s16) |
| Performs final quantization step on 8 signed 16-bit elements. More... | |
| template<bool is_bounded_relu> | |
| int16_t | finalize_quantization_int16 (int32_t in_value, int result_fixedpoint_multiplier, int32_t result_shift, int16_t min_s16, int16_t max_s16) |
| Performs final quantization step on single signed 16-bit element. More... | |
| float32x4x2_t | vdequantize_int16 (const int16x8_t &qv, float scale) |
| Dequantize a neon vector holding 8 16-bit quantized values. More... | |
| int16x8_t | vquantize_int16 (const float32x4x2_t &qv, float scale) |
| Quantize a neon vector holding 8 floating point values. More... | |
| float32x4x4_t | vdequantize (const int16x8x2_t &qv, const UniformQuantizationInfo &qi) |
| Dequantize a neon vector holding 16 16-bit quantized values. More... | |
| qsymm16x8x2_t | vquantize_qsymm16 (const float32x4x4_t &qv, const UniformQuantizationInfo &qi) |
| Quantize a neon vector holding 16 floating point values. More... | |
| int32x4x2_t | multiply_by_quantized_multiplier_2row (int32x4x2_t input, int32_t qmul, int32_t shift) |
| Multiply a neon vector using quantized multiplier and shift. More... | |
| template<typename T , unsigned int S, unsigned int dim, bool do_2D_norm> | |
| void | normalize_float (const Window &window, const ITensor *in, const ITensor *in_squared, ITensor *out, NormalizationLayerInfo ninfo) |
| Function to perform normalization depending on the given template dimension. More... | |
| inline ::std::ostream & | operator<< (::std::ostream &os, const ClComponentElementwiseBinary::Attributes::ElementwiseOp &op) |
| Formatted output of the pute::experimental::dynamic_fusion::ClComponentElementwiseBinary::Attributes::ElementwiseOp type. More... | |
| std::string | to_string (const ClComponentElementwiseBinary::Attributes::ElementwiseOp &op) |
| Formatted output of the arm_compute::experimental::dynamic_fusion::ClComponentElementwiseBinary::Attributes::ElementwiseOp type. More... | |
| Status | validate (const ITensorInfo *scores_in, const ITensorInfo *boxes_in, const ITensorInfo *batch_splits_in, const ITensorInfo *scores_out, const ITensorInfo *boxes_out, const ITensorInfo *classes, const ITensorInfo *batch_splits_out, const ITensorInfo *keeps, const ITensorInfo *keeps_size, const BoxNMSLimitInfo info) |
| inline ::std::istream & | operator>> (::std::istream &is, BorderMode &mode) |
| Formatted input of the BorderMode type. More... | |
| template<typename T > | |
| std::string | to_string_if_not_null (T *arg) |
| Formatted output if arg is not null. More... | |
| template<typename T > | |
| std::string | to_string (const T &val) |
| Fallback method: try to use std::to_string: More... | |
| template<typename T > | |
| ::std::ostream & | operator<< (::std::ostream &os, const std::vector< T > &args) |
| Formatted output of a vector of objects. More... | |
| template<typename T > | |
| std::string | to_string (const std::vector< T > &args) |
| Formatted output of a vector of objects. More... | |
| template<typename T > | |
| inline ::std::ostream & | operator<< (::std::ostream &os, const Dimensions< T > &dimensions) |
| Formatted output of the Dimensions type. More... | |
| inline ::std::ostream & | operator<< (::std::ostream &os, const RoundingPolicy &rounding_policy) |
| Formatted output of the RoundingPolicy type. More... | |
| inline ::std::ostream & | operator<< (::std::ostream &os, const WeightsInfo &weights_info) |
| Formatted output of the WeightsInfo type. More... | |
| inline ::std::ostream & | operator<< (::std::ostream &os, const ROIPoolingLayerInfo &pool_info) |
| Formatted output of the ROIPoolingInfo type. More... | |
| std::string | to_string (const ROIPoolingLayerInfo &pool_info) |
| Formatted output of the ROIPoolingInfo type. More... | |
| inline ::std::ostream & | operator<< (::std::ostream &os, const GEMMKernelInfo &gemm_info) |
| Formatted output of the GEMMKernelInfo type. More... | |
| inline ::std::ostream & | operator<< (::std::ostream &os, const GEMMLHSMatrixInfo &gemm_info) |
| Formatted output of the GEMMLHSMatrixInfo type. More... | |
| inline ::std::ostream & | operator<< (::std::ostream &os, const GEMMRHSMatrixInfo &gemm_info) |
| Formatted output of the GEMMRHSMatrixInfo type. More... | |
| std::string | to_string (const GEMMRHSMatrixInfo &gemm_info) |
| Formatted output of the GEMMRHSMatrixInfo type. More... | |
| std::string | to_string (const GEMMLHSMatrixInfo &gemm_info) |
| Formatted output of the GEMMLHSMatrixInfo type. More... | |
| std::string | to_string (const GEMMKernelInfo &gemm_info) |
| Formatted output of the GEMMKernelInfo type. More... | |
| inline ::std::ostream & | operator<< (::std::ostream &os, const BoundingBoxTransformInfo &bbox_info) |
| Formatted output of the BoundingBoxTransformInfo type. More... | |
| std::string | to_string (const BoundingBoxTransformInfo &bbox_info) |
| Formatted output of the BoundingBoxTransformInfo type. More... | |
| inline ::std::ostream & | operator<< (::std::ostream &os, const ComputeAnchorsInfo &anchors_info) |
| Formatted output of the ComputeAnchorsInfo type. More... | |
| std::string | to_string (const ComputeAnchorsInfo &anchors_info) |
| Formatted output of the ComputeAnchorsInfo type. More... | |
| inline ::std::ostream & | operator<< (::std::ostream &os, const GenerateProposalsInfo &proposals_info) |
| Formatted output of the GenerateProposalsInfo type. More... | |
| std::string | to_string (const GenerateProposalsInfo &proposals_info) |
| Formatted output of the GenerateProposalsInfo type. More... | |
| inline ::std::ostream & | operator<< (::std::ostream &os, const QuantizationInfo &qinfo) |
| Formatted output of the QuantizationInfo type. More... | |
| std::string | to_string (const QuantizationInfo &quantization_info) |
| Formatted output of the QuantizationInfo type. More... | |
| inline ::std::ostream & | operator<< (::std::ostream &os, const ActivationLayerInfo::ActivationFunction &act_function) |
| Formatted output of the activation function type. More... | |
| std::string | to_string (const arm_compute::ActivationLayerInfo &info) |
| Formatted output of the activation function info type. More... | |
| inline ::std::ostream & | operator<< (::std::ostream &os, const ActivationLayerInfo *info) |
| Formatted output of the activation function info. More... | |
| std::string | to_string (const arm_compute::ActivationLayerInfo::ActivationFunction &function) |
| Formatted output of the activation function type. More... | |
| inline ::std::ostream & | operator<< (::std::ostream &os, const NormType &norm_type) |
| Formatted output of the NormType type. More... | |
| std::string | to_string (const arm_compute::NormalizationLayerInfo &info) |
| Formatted output of NormalizationLayerInfo. More... | |
| inline ::std::ostream & | operator<< (::std::ostream &os, const NormalizationLayerInfo &info) |
| Formatted output of NormalizationLayerInfo. More... | |
| inline ::std::ostream & | operator<< (::std::ostream &os, const PoolingType &pool_type) |
| Formatted output of the PoolingType type. More... | |
| inline ::std::ostream & | operator<< (::std::ostream &os, const PoolingLayerInfo &info) |
| Formatted output of PoolingLayerInfo. More... | |
| std::string | to_string (const RoundingPolicy &rounding_policy) |
| Formatted output of RoundingPolicy. More... | |
| inline ::std::ostream & | operator<< (::std::ostream &os, const DataLayout &data_layout) |
| [Print DataLayout type] More... | |
| std::string | to_string (const arm_compute::DataLayout &data_layout) |
| Formatted output of the DataLayout type. More... | |
| inline ::std::ostream & | operator<< (::std::ostream &os, const DataLayoutDimension &data_layout_dim) |
| [Print DataLayout type] More... | |
| inline ::std::ostream & | operator<< (::std::ostream &os, const DataType &data_type) |
| Formatted output of the DataType type. More... | |
| std::string | to_string (const arm_compute::DataType &data_type) |
| Formatted output of the DataType type. More... | |
| inline ::std::ostream & | operator<< (::std::ostream &os, const Format &format) |
| Formatted output of the Format type. More... | |
| std::string | to_string (const Format &format) |
| Formatted output of the Format type. More... | |
| inline ::std::ostream & | operator<< (::std::ostream &os, const Channel &channel) |
| Formatted output of the Channel type. More... | |
| std::string | to_string (const Channel &channel) |
| Formatted output of the Channel type. More... | |
| inline ::std::ostream & | operator<< (::std::ostream &os, const BorderMode &mode) |
| Formatted output of the BorderMode type. More... | |
| inline ::std::ostream & | operator<< (::std::ostream &os, const BorderSize &border) |
| Formatted output of the BorderSize type. More... | |
| inline ::std::ostream & | operator<< (::std::ostream &os, const PaddingList &padding) |
| Formatted output of the PaddingList type. More... | |
| inline ::std::ostream & | operator<< (::std::ostream &os, const Multiples &multiples) |
| Formatted output of the Multiples type. More... | |
| inline ::std::ostream & | operator<< (::std::ostream &os, const InterpolationPolicy &policy) |
| Formatted output of the InterpolationPolicy type. More... | |
| inline ::std::ostream & | operator<< (::std::ostream &os, const SamplingPolicy &policy) |
| Formatted output of the SamplingPolicy type. More... | |
| inline ::std::ostream & | operator<< (std::ostream &os, const ITensorInfo *info) |
| Formatted output of the ITensorInfo type. More... | |
| inline ::std::ostream & | operator<< (::std::ostream &os, const TensorInfo &info) |
| Formatted output of the const TensorInfo& type. More... | |
| std::string | to_string (const TensorInfo &info) |
| Formatted output of the const TensorInfo& type. More... | |
| std::string | to_string (const ITensorInfo &info) |
| Formatted output of the const ITensorInfo& type. More... | |
| std::string | to_string (const ITensorInfo *info) |
| Formatted output of the const ITensorInfo* type. More... | |
| std::string | to_string (ITensorInfo *info) |
| Formatted output of the ITensorInfo* type. More... | |
| std::string | to_string (const ITensor *tensor) |
| Formatted output of the ITensorInfo type obtained from const ITensor* type. More... | |
| std::string | to_string (ITensor *tensor) |
| Formatted output of the ITensorInfo type obtained from the ITensor* type. More... | |
| std::string | to_string (ITensor &tensor) |
| Formatted output of the ITensorInfo type obtained from the ITensor& type. More... | |
| template<typename T > | |
| std::string | to_string (const Dimensions< T > &dimensions) |
| Formatted output of the Dimensions type. More... | |
| std::string | to_string (const Strides &stride) |
| Formatted output of the Strides type. More... | |
| std::string | to_string (const TensorShape &shape) |
| Formatted output of the TensorShape type. More... | |
| std::string | to_string (const Coordinates &coord) |
| Formatted output of the Coordinates type. More... | |
| inline ::std::ostream & | operator<< (::std::ostream &os, const GEMMReshapeInfo &info) |
| Formatted output of the GEMMReshapeInfo type. More... | |
| inline ::std::ostream & | operator<< (::std::ostream &os, const GEMMInfo &info) |
| Formatted output of the GEMMInfo type. More... | |
| inline ::std::ostream & | operator<< (::std::ostream &os, const Window::Dimension &dim) |
| Formatted output of the Window::Dimension type. More... | |
| inline ::std::ostream & | operator<< (::std::ostream &os, const Window &win) |
| Formatted output of the Window type. More... | |
| std::string | to_string (const WeightsInfo &info) |
| Formatted output of the WeightsInfo type. More... | |
| std::string | to_string (const GEMMReshapeInfo &info) |
| Formatted output of the GEMMReshapeInfo type. More... | |
| std::string | to_string (const GEMMInfo &info) |
| Formatted output of the GEMMInfo type. More... | |
| std::string | to_string (const Window::Dimension &dim) |
| Formatted output of the Window::Dimension type. More... | |
| std::string | to_string (const Window &win) |
| Formatted output of the Window& type. More... | |
| std::string | to_string (Window *win) |
| Formatted output of the Window* type. More... | |
| inline ::std::ostream & | operator<< (::std::ostream &os, const Rectangle &rect) |
| Formatted output of the Rectangle type. More... | |
| inline ::std::ostream & | operator<< (::std::ostream &os, const PaddingMode &mode) |
| Formatted output of the PaddingMode type. More... | |
| std::string | to_string (const PaddingMode &mode) |
| Formatted output of the PaddingMode type. More... | |
| inline ::std::ostream & | operator<< (::std::ostream &os, const PadStrideInfo &pad_stride_info) |
| Formatted output of the PadStrideInfo type. More... | |
| std::string | to_string (const PadStrideInfo &pad_stride_info) |
| Formatted output of the PadStrideInfo type. More... | |
| std::string | to_string (const BorderMode &mode) |
| Formatted output of the BorderMode type. More... | |
| std::string | to_string (const BorderSize &border) |
| Formatted output of the BorderSize type. More... | |
| std::string | to_string (const PaddingList &padding) |
| Formatted output of the PaddingList type. More... | |
| std::string | to_string (const Multiples &multiples) |
| Formatted output of the Multiples type. More... | |
| std::string | to_string (const InterpolationPolicy &policy) |
| Formatted output of the InterpolationPolicy type. More... | |
| std::string | to_string (const SamplingPolicy &policy) |
| Formatted output of the SamplingPolicy type. More... | |
| inline ::std::ostream & | operator<< (::std::ostream &os, const ConvertPolicy &policy) |
| Formatted output of the ConvertPolicy type. More... | |
| std::string | to_string (const ConvertPolicy &policy) |
| inline ::std::ostream & | operator<< (::std::ostream &os, const ArithmeticOperation &op) |
| Formatted output of the ArithmeticOperation type. More... | |
| std::string | to_string (const ArithmeticOperation &op) |
| Formatted output of the Arithmetic Operation. More... | |
| inline ::std::ostream & | operator<< (::std::ostream &os, const ReductionOperation &op) |
| Formatted output of the Reduction Operations. More... | |
| std::string | to_string (const ReductionOperation &op) |
| Formatted output of the Reduction Operations. More... | |
| inline ::std::ostream & | operator<< (::std::ostream &os, const ComparisonOperation &op) |
| Formatted output of the Comparison Operations. More... | |
| inline ::std::ostream & | operator<< (::std::ostream &os, const ElementWiseUnary &op) |
| Formatted output of the Elementwise unary Operations. More... | |
| std::string | to_string (const ComparisonOperation &op) |
| Formatted output of the Comparison Operations. More... | |
| std::string | to_string (const ElementWiseUnary &op) |
| Formatted output of the Elementwise unary Operations. More... | |
| std::string | to_string (const NormType &type) |
| Formatted output of the Norm Type. More... | |
| std::string | to_string (const PoolingType &type) |
| Formatted output of the Pooling Type. More... | |
| std::string | to_string (const PoolingLayerInfo &info) |
| Formatted output of the Pooling Layer Info. More... | |
| inline ::std::ostream & | operator<< (::std::ostream &os, const Size3D &size) |
| Formatted output of the Size3D type. More... | |
| std::string | to_string (const Size3D &type) |
| Formatted output of the Size3D type. More... | |
| inline ::std::ostream & | operator<< (::std::ostream &os, const Padding3D &padding3d) |
| Formatted output of the Padding3D type. More... | |
| std::string | to_string (const Padding3D &padding3d) |
| Converts a Padding3D to string. More... | |
| inline ::std::ostream & | operator<< (::std::ostream &os, const DimensionRoundingType &rounding_type) |
| Formatted output of the DimensionRoundingType type. More... | |
| inline ::std::ostream & | operator<< (::std::ostream &os, const Pooling3dLayerInfo &info) |
| Formatted output of the Pooling 3d Layer Info. More... | |
| std::string | to_string (const Pooling3dLayerInfo &info) |
| Formatted output of the Pooling 3d Layer Info. More... | |
| std::string | to_string (const PriorBoxLayerInfo &info) |
| Formatted output of the PriorBoxLayerInfo. More... | |
| inline ::std::ostream & | operator<< (::std::ostream &os, const Size2D &size) |
| Formatted output of the Size2D type. More... | |
| std::string | to_string (const Size2D &type) |
| Formatted output of the Size2D type. More... | |
| inline ::std::ostream & | operator<< (::std::ostream &os, const ConvolutionMethod &conv_method) |
| Formatted output of the ConvolutionMethod type. More... | |
| std::string | to_string (const ConvolutionMethod &conv_method) |
| Formatted output of the ConvolutionMethod type. More... | |
| inline ::std::ostream & | operator<< (::std::ostream &os, const GPUTarget &gpu_target) |
| Formatted output of the GPUTarget type. More... | |
| std::string | to_string (const GPUTarget &gpu_target) |
| Formatted output of the GPUTarget type. More... | |
| inline ::std::ostream & | operator<< (::std::ostream &os, const DetectionWindow &detection_window) |
| Formatted output of the DetectionWindow type. More... | |
| inline ::std::ostream & | operator<< (::std::ostream &os, const DetectionOutputLayerCodeType &detection_code) |
| Formatted output of the DetectionOutputLayerCodeType type. More... | |
| std::string | to_string (const DetectionOutputLayerCodeType &detection_code) |
| Formatted output of the DetectionOutputLayerCodeType type. More... | |
| inline ::std::ostream & | operator<< (::std::ostream &os, const DetectionOutputLayerInfo &detection_info) |
| Formatted output of the DetectionOutputLayerInfo type. More... | |
| std::string | to_string (const DetectionOutputLayerInfo &detection_info) |
| Formatted output of the DetectionOutputLayerInfo type. More... | |
| inline ::std::ostream & | operator<< (::std::ostream &os, const DetectionPostProcessLayerInfo &detection_info) |
| Formatted output of the DetectionPostProcessLayerInfo type. More... | |
| std::string | to_string (const DetectionPostProcessLayerInfo &detection_info) |
| Formatted output of the DetectionPostProcessLayerInfo type. More... | |
| std::string | to_string (const DetectionWindow &detection_window) |
| Formatted output of the DetectionWindow type. More... | |
| inline ::std::ostream & | operator<< (::std::ostream &os, const PriorBoxLayerInfo &info) |
| Formatted output of PriorBoxLayerInfo. More... | |
| inline ::std::ostream & | operator<< (::std::ostream &os, const WinogradInfo &info) |
| Formatted output of the WinogradInfo type. More... | |
| std::string | to_string (const WinogradInfo &type) |
| std::string | to_string (const CLTunerMode val) |
| Convert a CLTunerMode value to a string. More... | |
| std::string | to_string (CLGEMMKernelType val) |
| Converts a CLGEMMKernelType to string. More... | |
| inline ::std::ostream & | operator<< (::std::ostream &os, const CLTunerMode &val) |
| [Print CLTunerMode type] More... | |
| inline ::std::ostream & | operator<< (::std::ostream &os, const ConvolutionInfo &conv_info) |
| Formatted output of the ConvolutionInfo type. More... | |
| std::string | to_string (const ConvolutionInfo &info) |
| Converts a ConvolutionInfo to string. More... | |
| inline ::std::ostream & | operator<< (::std::ostream &os, const FullyConnectedLayerInfo &layer_info) |
| Formatted output of the FullyConnectedLayerInfo type. More... | |
| std::string | to_string (const FullyConnectedLayerInfo &info) |
| Converts a FullyConnectedLayerInfo to string. More... | |
| inline ::std::ostream & | operator<< (::std::ostream &os, const GEMMLowpOutputStageType &gemm_type) |
| Formatted output of the GEMMLowpOutputStageType type. More... | |
| std::string | to_string (const GEMMLowpOutputStageType &gemm_type) |
| Converts a GEMMLowpOutputStageType to string. More... | |
| inline ::std::ostream & | operator<< (::std::ostream &os, const GEMMLowpOutputStageInfo &gemm_info) |
| Formatted output of the GEMMLowpOutputStageInfo type. More... | |
| std::string | to_string (const GEMMLowpOutputStageInfo &gemm_info) |
| Converts a GEMMLowpOutputStageInfo to string. More... | |
| inline ::std::ostream & | operator<< (::std::ostream &os, const Conv2dInfo &conv_info) |
| Formatted output of the Conv2dInfo type. More... | |
| std::string | to_string (const Conv2dInfo &conv_info) |
| Converts a Conv2dInfo to string. More... | |
| inline ::std::ostream & | operator<< (::std::ostream &os, const PixelValue &pixel_value) |
| Formatted output of the PixelValue type. More... | |
| std::string | to_string (const PixelValue &pixel_value) |
| Converts a PixelValue to string. More... | |
| inline ::std::ostream & | operator<< (::std::ostream &os, const ScaleKernelInfo &scale_info) |
| Formatted output of the ScaleKernelInfo type. More... | |
| std::string | to_string (const ScaleKernelInfo &scale_info) |
| Converts a ScaleKernelInfo to string. More... | |
| inline ::std::ostream & | operator<< (::std::ostream &os, const FFTDirection &fft_dir) |
| Formatted output of the FFTDirection type. More... | |
| std::string | to_string (const FFTDirection &fft_dir) |
| Converts a FFT1DInfo to string. More... | |
| inline ::std::ostream & | operator<< (::std::ostream &os, const FFT1DInfo &fft1d_info) |
| Formatted output of the FFT1DInfo type. More... | |
| std::string | to_string (const FFT1DInfo &fft1d_info) |
| Converts a FFT1DInfo to string. More... | |
| inline ::std::ostream & | operator<< (::std::ostream &os, const FFT2DInfo &fft2d_info) |
| Formatted output of the FFT2DInfo type. More... | |
| std::string | to_string (const FFT2DInfo &fft2d_info) |
| Converts a FFT2DInfo to string. More... | |
| inline ::std::ostream & | operator<< (::std::ostream &os, const Coordinates2D &coord_2d) |
| Formatted output of the Coordinates2D type. More... | |
| std::string | to_string (const Coordinates2D &coord_2d) |
| Converts a Coordinates2D to string. More... | |
| inline ::std::ostream & | operator<< (::std::ostream &os, const FuseBatchNormalizationType &fuse_type) |
| Formatted output of the FuseBatchNormalizationType type. More... | |
| std::string | to_string (const FuseBatchNormalizationType &fuse_type) |
| Converts a FuseBatchNormalizationType to string. More... | |
| inline ::std::ostream & | operator<< (::std::ostream &os, const SoftmaxKernelInfo &info) |
| Formatted output of the SoftmaxKernelInfo type. More... | |
| std::string | to_string (const SoftmaxKernelInfo &info) |
| Converts a SoftmaxKernelInfo to string. More... | |
| template<typename T > | |
| ::std::ostream & | operator<< (::std::ostream &os, const LSTMParams< T > &lstm_params) |
| Formatted output of the ScaleKernelInfo type. More... | |
| template<typename T > | |
| std::string | to_string (const LSTMParams< T > &lstm_params) |
| Converts a LSTMParams to string. More... | |
| std::string | to_string (const uint8_t num) |
| Converts a LSTMParams to string. More... | |
| inline ::std::ostream & | operator<< (::std::ostream &os, const NMSType &nms_type) |
| Available non maxima suppression types. More... | |
| std::string | to_string (const NMSType nms_type) |
| Converts a NMSType to string. More... | |
| inline ::std::ostream & | operator<< (::std::ostream &os, const BoxNMSLimitInfo &info) |
| Formatted output of the BoxNMSLimitInfo type. More... | |
| std::string | to_string (const BoxNMSLimitInfo &info) |
| Converts a BoxNMSLimitInfo to string. More... | |
| std::string | to_string (const DimensionRoundingType &rounding_type) |
| Converts a DimensionRoundingType to string. More... | |
| inline ::std::ostream & | operator<< (::std::ostream &os, const Conv3dInfo &conv3d_info) |
| Formatted output of the Conv3dInfo type. More... | |
| std::string | to_string (const Conv3dInfo &conv3d_info) |
| Formatted output of the Conv3dInfo type. More... | |
| std::string | to_string (const WeightFormat wf) |
| Formatted output of the arm_compute::WeightFormat type. More... | |
| inline ::std::ostream & | operator<< (::std::ostream &os, const arm_compute::WeightFormat &wf) |
| Formatted output of the arm_compute::WeightFormat type. More... | |
| std::string | to_string (const std::tuple< TensorShape, TensorShape, arm_compute::WeightFormat > values) |
| Formatted output of the std::tuple<TensorShape, TensorShape, arm_compute::WeightFormat> tuple. More... | |
| inline ::std::ostream & | operator<< (::std::ostream &os, const Padding2D &padding2d) |
| Formatted output of the Padding2D type. More... | |
| std::string | to_string (const Padding2D &padding2d) |
| Converts a Padding2D to string. More... | |
| inline ::std::ostream & | operator<< (::std::ostream &os, const experimental::dynamic_fusion::Pool2dAttributes &pool2d_attr) |
| Formatted output of the arm_compute::experimental::dynamic_fusion::Pool2dAttributes type. More... | |
| std::string | to_string (const experimental::dynamic_fusion::Pool2dAttributes &pool2d_attr) |
| Formatted output of the arm_compute::experimental::dynamic_fusion::Pool2dAttributes type. More... | |
| inline ::std::ostream & | operator<< (::std::ostream &os, const experimental::dynamic_fusion::GpuPool2dSettings &settings) |
| Formatted output of the arm_compute::experimental::dynamic_fusion::GpuPool2dSettings type. More... | |
| std::string | to_string (const experimental::dynamic_fusion::GpuPool2dSettings &settings) |
| Formatted output of the arm_compute::experimental::dynamic_fusion::GpuPool2dSettings type. More... | |
| inline ::std::ostream & | operator<< (::std::ostream &os, const experimental::dynamic_fusion::Conv2dAttributes &conv2d_attr) |
| Formatted output of the arm_compute::experimental::dynamic_fusion::Conv2dAttributes type. More... | |
| std::string | to_string (const experimental::dynamic_fusion::Conv2dAttributes &conv2d_attr) |
| Formatted output of the arm_compute::experimental::dynamic_fusion::Conv2dAttributes type. More... | |
| inline ::std::ostream & | operator<< (::std::ostream &os, const experimental::dynamic_fusion::CastAttributes &cast_attr) |
| Formatted output of the arm_compute::experimental::dynamic_fusion::CastAttributes type. More... | |
| std::string | to_string (const experimental::dynamic_fusion::CastAttributes &cast_attr) |
| Formatted output of the arm_compute::experimental::dynamic_fusion::CastAttributes type. More... | |
| inline ::std::ostream & | operator<< (::std::ostream &os, const experimental::dynamic_fusion::DepthwiseConv2dAttributes &dw_conv2d_attr) |
| Formatted output of the arm_compute::experimental::dynamic_fusion::DepthwiseConv2dAttributes type. More... | |
| std::string | to_string (const experimental::dynamic_fusion::DepthwiseConv2dAttributes &dw_conv2d_attr) |
| Formatted output of the arm_compute::experimental::dynamic_fusion::DepthwiseConv2dAttributes type. More... | |
| inline ::std::ostream & | operator<< (::std::ostream &os, const experimental::dynamic_fusion::ClampAttributes &clamp_attr) |
| Formatted output of the arm_compute::experimental::dynamic_fusion::ClampAttributes type. More... | |
| std::string | to_string (const experimental::dynamic_fusion::ClampAttributes &clamp_attr) |
| Formatted output of the arm_compute::experimental::dynamic_fusion::ClampAttributes type. More... | |
| inline ::std::ostream & | operator<< (::std::ostream &os, const experimental::dynamic_fusion::ResizeAttributes &resize_attr) |
| Formatted output of the arm_compute::experimental::dynamic_fusion::ResizeAttributes type. More... | |
| std::string | to_string (const experimental::dynamic_fusion::ResizeAttributes &resize_attr) |
| Formatted output of the arm_compute::experimental::dynamic_fusion::ResizeAttributes type. More... | |
| inline ::std::ostream & | operator<< (::std::ostream &os, const experimental::dynamic_fusion::SoftmaxAttributes &softmax_attr) |
| Formatted output of the arm_compute::experimental::dynamic_fusion::SoftmaxAttributes type. More... | |
| std::string | to_string (const experimental::dynamic_fusion::SoftmaxAttributes &softmax_attr) |
| Formatted output of the arm_compute::experimental::dynamic_fusion::SoftmaxAttributes type. More... | |
| inline ::std::ostream & | operator<< (::std::ostream &os, const arm_compute::MatMulInfo &matmul_info) |
| Formatted output of the arm_compute::MatMulInfo type. More... | |
| std::string | to_string (const arm_compute::MatMulInfo &matmul_info) |
| Formatted output of the arm_compute::MatMulInfo type. More... | |
| inline ::std::ostream & | operator<< (::std::ostream &os, const arm_compute::MatMulKernelInfo &matmul_info) |
| Formatted output of the arm_compute::MatMulKernelInfo type. More... | |
| std::string | to_string (const arm_compute::MatMulKernelInfo &matmul_info) |
| Formatted output of the arm_compute::MatMulKernelInfo type. More... | |
| inline ::std::ostream & | operator<< (::std::ostream &os, const arm_compute::CpuMatMulSettings &settings) |
| Formatted output of the arm_compute::CpuMatMulSettings type. More... | |
| std::string | to_string (const arm_compute::CpuMatMulSettings &settings) |
| Formatted output of the arm_compute::CpuMatMulSettings type. More... | |
| inline ::std::ostream & | operator<< (::std::ostream &os, const ScatterFunction &function) |
| Formatted output of the scatter function type. More... | |
| std::string | to_string (const arm_compute::ScatterFunction &func) |
| Formatted output of the arm_compute::ScatterFunction type. More... | |
| inline ::std::ostream & | operator<< (::std::ostream &os, const arm_compute::ScatterInfo &info) |
| Formatted output of the arm_compute::ScatterInfo type. More... | |
| std::string | to_string (const arm_compute::ScatterInfo &info) |
| Formatted output of the arm_compute::ScatterInfo type. More... | |
Variables | |
| constexpr size_t | MAX_DIMS = 6 |
| Constant value used to indicate maximum dimensions of a Window, TensorShape and Coordinates. More... | |
| const std::array< float32x4_t, 8 > | log_tab |
| Logarithm polynomial coefficients. More... | |
| constexpr float | te_sin_coeff2 = 0.166666666666f |
| Sin polynomial coefficients. More... | |
| constexpr float | te_sin_coeff3 = 0.05f |
| constexpr float | te_sin_coeff4 = 0.023809523810f |
| constexpr float | te_sin_coeff5 = 0.013888888889f |
| const std::array< ErfLutEntry< float >, 513 > | erf_f32_lut |
| The lookup table for FP32 erf(x) calculation. More... | |
Copyright (c) 2017-2024 Arm Limited.
Synced with tests/validation/dynamic_fusion/gpu/cl/DirectConv2d.cpp Please check there for any differences in the coverage.
A DotMLGO file parser (LL(k) parser)
[CLReshapeLayer snippet]
[ClReshapeKernel Kernel]
[NEReshapeLayerKernel Kernel]
This file contains all available output stages for GEMMLowp.
This file contains all available output stages for GEMMLowp on OpenCL.
The following symbols have been moved to: half PermutationVector Format DataType DataLayout DataLayoutDimension PadStrideInfo WeightFormat Channel DimensionRoundingType.
CoreTypes.h groups together essential small types that are used across functions.
Copyright (c) 2017-2021, 2024 Arm Limited.
Copyright (c) 2018-2022 Arm Limited.
Copyright (c) 2019-2023 Arm Limited.
Copyright (c) 2017-2021 Arm Limited.
Copyright (c) 2021-2024 Arm Limited.
Copyright (c) 2023 Arm Limited.
Copyright (c) 2021-2022 Arm Limited.
Copyright (c) 2021 Arm Limited.
Copyright (c) 2017-2021, 2023-2024 Arm Limited.
SPDX-License-Identifier: MIT
Permission is hereby granted, free of charge, to any person obtaining a copy of this software and associated documentation files (the "Software"), to deal in the Software without restriction, including without limitation the rights to use, copy, modify, merge, publish, distribute, sublicense, and/or sell copies of the Software, and to permit persons to whom the Software is furnished to do so, subject to the following conditions:
The above copyright notice and this permission notice shall be included in all copies or substantial portions of the Software.
THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE SOFTWARE.
The following symbols have been moved to: ActivationFunction ActivationLayerInfo The following symbols have been moved to: ConvolutionInfo The following symbols have been moved to: FullyConnectedLayerInfo The following symbols have been moved to: GEMMLowpOutputStageType GEMMLowpOutputStageInfo GEMMInfo The following symbols have been moved to: MatMulInfo
In gemmlowp, the "output stage" is the process that takes a final int32 accumulator value (the output of CLGEMMLowpMatrixMultiplyCore), and processes it to obtain the final QASYMM8/QASYMM8_SIGNED value.
More information about the GEMMLowp output stage can be found at https://github.com/google/gemmlowp/blob/master/doc/output.md
In gemmlowp, the "output stage" is the process that takes a final int32 accumulator value (the output of NEGEMMLowpMatrixMultiplyCore), and processes it to obtain the final ASYMM8 value.
More information about the GEMMLowp output stage can be found at https://github.com/google/gemmlowp/blob/master/doc/output.md
The grammar of DotMLGO is defined as the following ENBF:
delim = "," | "\n"; // Note that delimiters are omitted from the definition below
mlgo = header, heuristics-table, {heuristic-tree};
header = "<header>", gemm-version, ip-type, "</header>"; gemm-version = "gemm-version", "[", int, int, int, "]"; ip-type = "ip-type", ("gpu" | "cpu");
heiristics-table = "<heuristics-table>", {heuristics-table-entry}, "</heuristics-table>"; heuristics-table-entry = entry-id, ip-name, num-cores, data-type, gpu-priority, gpu-behavior, heuristic-type, free-vars; entry-id = int; ip-name = char-sequence; num-cores = int; data-type = "f32" | "f16" | "qasymm8"; gpu-priority = "best-performance" | "best-memory-usage"; gpu-behavior = "static" | "dynamic"; heuristic-type = "gemm-type" | "gemm-config-native" | "gemm-config-reshaped-only-rhs" | "gemm-config-reshaped"; free-vars = "[", {char-sequence}, "]";
heuristic-tree = "<heuristic", entry-id, ">", {tree-node}, "</heuristic>"; tree-node = branch-node | leaf-node; branch-node = "b", entry-id, lhs-type, lhs-value, conditional-op, rhs-type, rhs-value, true-node, false-node; lhs-type = comparator-type; lhs-value = comparator-value; rhs-type = comparator-type; rhs-value = comparator-value; comparator-type = "var" | "num" | "enum"; comparator-value = char-sequence | float; conditional-op = "<" | "<=" | "==" | ">=" | ">"; true-node = entry-id; false-node = entry-id; leaf-node = "l", entry-id, heuristic-type, leaf-value; leaf-value = gemm-type | gemm-config-native | gemm-config-reshaped-only-rhs | gemm-config-reshaped gemm-type = "native" | "reshaped-only-rhs" | "reshaped"; gemm-config-native = "[", int, int, int, "]"; gemm-config-reshaped-only-rhs = "[", int, int, int, int, bool, bool, bool, "]"; gemm-config-reshaped = "[", int, int, int, int, int, bool, bool, bool, bool, "]";
| using BiStrides = Coordinates |
Basic function to run equal comparison.
Definition at line 131 of file CLComparison.h.
| using CLFloatArray = CLArray<cl_float> |
Basic function to run greater comparison.
Definition at line 135 of file CLComparison.h.
Basic function to run greater-equal comparison.
Definition at line 137 of file CLComparison.h.
OpenCL Image.
Definition at line 104 of file CLTensor.h.
| using CLInt16Array = CLArray<cl_short> |
| using CLInt32Array = CLArray<cl_int> |
Basic function to run less comparison.
Definition at line 139 of file CLComparison.h.
Basic function to run less-equal comparison.
Definition at line 141 of file CLComparison.h.
| using CLLogSoftmaxLayer = CLSoftmaxLayerGeneric<true> |
Definition at line 110 of file CLSoftmaxLayer.h.
Basic function to run not equal comparison.
Definition at line 133 of file CLComparison.h.
| using CLSoftmaxLayer = CLSoftmaxLayerGeneric<false> |
Definition at line 109 of file CLSoftmaxLayer.h.
| using CLUInt16Array = CLArray<cl_ushort> |
| using CLUInt32Array = CLArray<cl_uint> |
| using CLUInt8Array = CLArray<cl_uchar> |
| typedef float float32_t |
Definition at line 33 of file CpuTypes.h.
| using FloatArray = Array<float> |
| using GroupMappings = std::map<size_t, MemoryMappings> |
| using half = half_float::half |
16-bit floating point type
Definition at line 36 of file CoreTypes.h.
| using ICLFloatArray = ICLArray<cl_float> |
Interface for OpenCL Array of floats.
Definition at line 126 of file ICLArray.h.
Definition at line 114 of file ICLTensor.h.
| using ICLInt16Array = ICLArray<cl_short> |
Interface for OpenCL Array of int16s.
Definition at line 122 of file ICLArray.h.
| using ICLInt32Array = ICLArray<cl_int> |
Interface for OpenCL Array of int32s.
Definition at line 124 of file ICLArray.h.
| using ICLUInt16Array = ICLArray<cl_ushort> |
Interface for OpenCL Array of uint16s.
Definition at line 118 of file ICLArray.h.
| using ICLUInt32Array = ICLArray<cl_uint> |
Interface for OpenCL Array of uint32s.
Definition at line 120 of file ICLArray.h.
| using ICLUInt8Array = ICLArray<cl_uchar> |
Interface for OpenCL Array of uint8s.
Definition at line 116 of file ICLArray.h.
| using IFloatArray = IArray<float> |
| using IInt16Array = IArray<int16_t> |
| using IInt32Array = IArray<int32_t> |
| typedef ICPPKernel INEKernel |
Common interface for all kernels implemented in Neon.
Definition at line 39 of file INEOperator.h.
| using Int16Array = Array<int16_t> |
| using Int32Array = Array<int32_t> |
| using IUInt16Array = IArray<uint16_t> |
| using IUInt32Array = IArray<uint32_t> |
| using IUInt8Array = IArray<uint8_t> |
| using lock_guard = std::lock_guard<Mutex> |
| using MemoryMappings = std::map<IMemory *, size_t> |
A map of (handle, index/offset), where handle is the memory handle of the object to provide the memory for and index/offset is the buffer/offset from the pool that should be used.
Definition at line 56 of file IOperator.h.
| using Multiples = std::vector<uint32_t> |
Definition at line 91 of file NEElementwiseUnaryLayer.h.
Basic function to run equal comparison.
Definition at line 468 of file NEElementwiseOperations.h.
Definition at line 88 of file NEElementwiseUnaryLayer.h.
Basic function to run greater comparison.
Definition at line 472 of file NEElementwiseOperations.h.
Basic function to run greater-equal comparison.
Definition at line 474 of file NEElementwiseOperations.h.
Basic function to run less comparison.
Definition at line 476 of file NEElementwiseOperations.h.
Basic function to run less-equal comparison.
Definition at line 478 of file NEElementwiseOperations.h.
Definition at line 90 of file NEElementwiseUnaryLayer.h.
| using NELogSoftmaxLayer = NESoftmaxLayerGeneric<true> |
Definition at line 98 of file NESoftmaxLayer.h.
Definition at line 89 of file NEElementwiseUnaryLayer.h.
Basic function to run not equal comparison.
Definition at line 470 of file NEElementwiseOperations.h.
Definition at line 92 of file NEElementwiseUnaryLayer.h.
Definition at line 87 of file NEElementwiseUnaryLayer.h.
| using NEScheduler = Scheduler |
CPU Scheduler.
Definition at line 32 of file NEScheduler.h.
Definition at line 93 of file NEElementwiseUnaryLayer.h.
| using NESoftmaxLayer = NESoftmaxLayerGeneric<false> |
Definition at line 97 of file NESoftmaxLayer.h.
| typedef cpu::CpuPRelu OperatorType |
Definition at line 40 of file CLGEMM.cpp.
| using PaddingInfo = std::pair<uint32_t, uint32_t> |
| using PaddingList = std::vector<PaddingInfo> |
| using PaddingSize = BorderSize |
| using PermutationVector = Strides |
Permutation vector.
Definition at line 38 of file CoreTypes.h.
| using qasymm16_t = uint16_t |
16 bit quantized asymmetric scalar value
Definition at line 39 of file QuantizationInfo.h.
| using qasymm8_signed_t = int8_t |
8 bit signed quantized asymmetric scalar value
Definition at line 36 of file QuantizationInfo.h.
| using qasymm8_t = uint8_t |
8 bit quantized asymmetric scalar value
Definition at line 37 of file QuantizationInfo.h.
| using qasymm8x16_signed_t = int8x16_t |
| using qasymm8x16_t = uint8x16_t |
| using qasymm8x8_signed_t = int8x8_t |
| using qasymm8x8_t = uint8x8_t |
| using qasymm8x8x2_signed_t = int8x8x2_t |
| using qasymm8x8x2_t = uint8x8x2_t |
| using qasymm8x8x3_signed_t = int8x8x3_t |
| using qasymm8x8x3_t = uint8x8x3_t |
| using qasymm8x8x4_signed_t = int8x8x4_t |
| using qasymm8x8x4_t = uint8x8x4_t |
| typedef int16_t qsymm16_t |
16 bit quantized symmetric scalar value
Definition at line 38 of file QuantizationInfo.h.
| using qsymm16x8_t = int16x8_t |
| using qsymm16x8x2_t = int16x8x2_t |
| using qsymm8_t = int8_t |
| using UInt16Array = Array<uint16_t> |
| using UInt32Array = Array<uint32_t> |
| using UInt8Array = Array<uint8_t> |
| using unique_lock = std::unique_lock<Mutex> |
| using WorkspaceData = std::vector<WorkspaceDataElement<TensorType> > |
Definition at line 52 of file MemoryHelpers.h.
|
strong |
Available activation functions.
Definition at line 41 of file ActivationLayerInfo.h.
|
strong |
|
strong |
|
strong |
|
strong |
|
strong |
Available channels.
Definition at line 41 of file CoreTypes.h.
|
strong |
|
strong |
OpenCL GEMM kernel types.
Definition at line 31 of file CLTypes.h.
|
strong |
| enum CLKernelType |
|
strong |
< OpenCL tuner modes
Definition at line 35 of file CLTunerTypes.h.
|
strong |
|
strong |
Supported comparison operations.
Definition at line 132 of file Types.h.
|
strong |
Policy to handle integer overflow.
| Enumerator | |
|---|---|
| WRAP | Wrap around. |
| SATURATE | Saturate. |
|
strong |
|
strong |
CPU models types.
| Enumerator | |
|---|---|
| X | |
| GENERIC | |
| GENERIC_FP16 | |
| GENERIC_FP16_DOT | |
| A53 | |
| A55r0 | |
| A55r1 | |
| A35 | |
| A73 | |
| A76 | |
| A510 | |
| X1 | |
| V1 | |
| A64FX | |
| N1 | |
Definition at line 59 of file CPPTypes.h.
|
strong |
[DataLayout enum definition]
Supported tensor data layouts
Definition at line 110 of file CoreTypes.h.
|
strong |
[DataLayout enum definition]
Supported tensor data layout dimensions
| Enumerator | |
|---|---|
| CHANNEL | channel |
| HEIGHT | height |
| WIDTH | width |
| DEPTH | depth |
| BATCHES | batches |
Definition at line 121 of file CoreTypes.h.
|
strong |
Available data types.
Definition at line 83 of file CoreTypes.h.
|
strong |
|
strong |
|
strong |
|
strong |
|
strong |
Dimension rounding type when down-scaling on CNNs.
| Enumerator | |
|---|---|
| FLOOR | Floor rounding. |
| CEIL | Ceil rounding. |
Definition at line 133 of file CoreTypes.h.
|
strong |
|
strong |
|
strong |
|
strong |
FFT direction to use.
| Enumerator | |
|---|---|
| Forward | |
| Inverse | |
Definition at line 35 of file FunctionDescriptors.h.
|
strong |
Image colour formats.
Definition at line 58 of file CoreTypes.h.
|
strong |
|
strong |
GEMMLowp output stage type.
Definition at line 36 of file GEMMInfo.h.
|
strong |
Available GPU Targets.
Definition at line 34 of file GPUTarget.h.
|
strong |
|
strong |
Interpolation method.
Definition at line 360 of file Types.h.
|
strong |
|
strong |
|
strong |
|
strong |
|
strong |
|
strong |
|
strong |
|
strong |
Rounding method.
Definition at line 30 of file Rounding.h.
|
strong |
|
strong |
|
strong |
|
strong |
| enum TensorType : int32_t |
Memory type.
Definition at line 38 of file Types.h.
|
strong |
Memory layouts for the weights tensor.
The other values OHWIo{interleave_by}i{block_by} describe the memory layout of a 4D tensor with layout OHWI that has been transformed into a 4D tensor with dimensions O'HWI' where:
O' = first multiple of {interleave_by} s.t. O<=O' I' = first multiple of {block_by} s.t. I<=I'
The total size of the dst tensor is O' x H x W x I'
The access function of the tensor with layout OHWIo{interleave_by}i{block_by} and size O'HWI' is a 6-parameter access function, where the 6 parameters are computed as follows:
x5 = floor(o/{interleave_by}) RANGE [0, O'/{interleave_by} -1] SIZE: O'/{interleave_by}
x4 = h RANGE [0, H-1] SIZE: H x3 = w RANGE [0, W-1] SIZE: W x2 = floor(i/{block_by}) RANGE [0, I'/{block_by} -1] SIZE: I'/{block_by} x1 = o%{interleave_by} RANGE [0, {interleave_by} -1] SIZE: {interleave_by} x0 = i%{block_by} RANGE [0, {block_by} -1] SIZE: {block_by} TOTAL SIZE: O' * H * W * I'
4D 6D
value(o, h, w, i) = x5 * H * W * I' * {interleave_by}
Notice that in arm_gemm the 4D tensor of dimension O'HWI' created for the OHWIo{interleave_by}i{block_by} format is in reality seen as a 2D tensor, where the number of rows is O'/{interleave_by} and the number of columns is {interleave_by} * H * W * I'.
The postfix *_bf16 is for the memory layout needed for the fast-mode kernels, in which the weights are passed in bfloat16 format.
Definition at line 311 of file CoreTypes.h.
|
inline |
Decrease required in steps of step until it's less than available.
| [in] | required | Number of required bytes. |
| [in] | available | Number of available bytes. |
| [in] | step | Step size used to decrease required bytes. |
available that is a multiple of step Definition at line 47 of file IAccessWindow.h.
References ARM_COMPUTE_ERROR_ON, GemmTuner::required, and arm_compute::cpu::step.
Referenced by AccessWindowTranspose::update_window_if_needed(), and AccessWindowRectangle::update_window_if_needed().
|
inline |
Adjust tensor shape size if width or height are odd for a given multi-planar format.
No modification is done for other formats.
| [in,out] | shape | Tensor shape of 2D size |
| [in] | format | Format of the tensor |
Definition at line 338 of file Validate.h.
References update_supported_ops::format, has_format_horizontal_subsampling(), has_format_vertical_subsampling(), arm_compute::test::validation::shape, and arm_compute::utils::cast::U.
|
inline |
Increase required in steps of step until it's greater than available.
| [in] | required | Number of required bytes. |
| [in] | available | Number of available bytes. |
| [in] | step | Step size used to increase required bytes. |
available that is a multiple of step Definition at line 63 of file IAccessWindow.h.
References ARM_COMPUTE_ERROR_ON, GemmTuner::required, and arm_compute::cpu::step.
Referenced by AccessWindowTranspose::update_window_if_needed(), and AccessWindowRectangle::update_window_if_needed().
|
inline |
Returns the adjusted vector size in case it is less than the input's first dimension, getting rounded down to its closest valid vector size.
| [in] | vec_size | vector size to be adjusted |
| [in] | dim0 | size of the first dimension |
Definition at line 38 of file AdjustVecSize.h.
References ARM_COMPUTE_ERROR_ON.
Referenced by ClTransposedConvolutionKernel::configure(), ClFloorKernel::configure(), ClTransposeKernel::configure(), ClCopyKernel::configure(), ClElementWiseUnaryKernel::configure(), ClMatMulLowpNativeMMULKernel::configure(), ClWidthConcatenate2TensorsKernel::configure(), ClPool2dKernel::configure(), ClPool3dKernel::configure(), ClHeightConcatenateKernel::configure(), ClScaleKernel::configure(), ClWidthConcatenateKernel::configure(), ClWidthConcatenate4TensorsKernel::configure(), ClActivationKernel::configure(), ClMatMulNativeKernel::configure(), ClBatchConcatenateKernel::configure(), ClDepthConcatenateKernel::configure(), ClMatMulLowpNativeKernel::configure(), CLBitwiseKernel::configure(), ClGemmLowpQuantizeDownInt32ScaleByFixedPointKernel::configure(), CLChannelShuffleLayerKernel::configure(), ClIndirectConv2dKernel::configure(), CLSelectKernel::configure(), ClGemmLowpQuantizeDownInt32ScaleKernel::configure(), ClGemmLowpQuantizeDownInt32ScaleByFloatKernel::configure(), CLNormalizationLayerKernel::configure(), ClSoftmaxKernel::configure(), CLComparisonKernel::configure(), ClCastKernel::configure(), ClGemmLowpOffsetContributionKernel::configure(), ClGemmLowpOffsetContributionOutputStageKernel::configure(), CLMeanStdDevNormalizationKernel::configure(), CLNormalizePlanarYUVLayerKernel::configure(), CLReductionOperationKernel::configure(), CLRangeKernel::configure(), ClDirectConv2dKernel::configure(), ClDirectConv3dKernel::configure(), CLL2NormalizeLayerKernel::configure(), ClMatMulNativeMMULKernel::configure(), CLPadLayerKernel::configure(), ClMulKernel::configure(), CLArgMinMaxLayerKernel::configure(), CLDepthwiseConvolutionLayerNativeKernel::configure(), CLBatchNormalizationLayerKernel::configure(), ClGemmLowpMatrixBReductionKernel::configure(), GpuCkwCast::get_window(), GpuCkwElementwiseBinary::get_window(), GpuCkwActivation::get_window(), GpuCkwResize::get_window(), GpuCkwPool2d::get_window(), GpuCkwDirectConv2d::get_window(), GpuCkwMatMul::get_window(), arm_compute::opencl::kernels::validate_and_configure_window_for_mmul_kernels(), GpuCkwDirectConv2d::write_component_code(), and GpuCkwMatMul::write_component_code().
| bool arm_matrix_multiply_supported | ( | const cl::Device & | device | ) |
Helper function to check whether the cl_arm_matrix_multiply extension is supported.
| [in] | device | A CL device |
Definition at line 499 of file CLHelpers.cpp.
References device_supports_extension().
Referenced by ClMatMulLowpNativeMMULKernel::validate(), and ClMatMulNativeMMULKernel::validate().
| bool arm_non_uniform_workgroup_supported | ( | const cl::Device & | device | ) |
Helper function to check whether the arm_non_uniform_work_group_size extension is supported.
| [in] | device | A CL device |
Definition at line 232 of file CLHelpers.cpp.
References device_supports_extension().
|
inline |
Auto initialize the tensor info (shape, number of channels and data type) if the current assignment is empty.
| [in,out] | info | Tensor info used to check and assign. |
| [in] | shape | New shape. |
| [in] | num_channels | New number of channels. |
| [in] | data_type | New data type |
| [in] | quantization_info | (Optional) New quantization info |
Definition at line 43 of file AutoConfiguration.h.
References arm_compute::test::validation::data_type, arm_compute::test::validation::info, and arm_compute::test::validation::shape.
Referenced by CpuDequantizeKernel::configure(), CpuTransposeKernel::configure(), ClTransposedConvolutionKernel::configure(), ClTransposeKernel::configure(), ClDequantizeKernel::configure(), ClFloorKernel::configure(), CpuPermuteKernel::configure(), CpuFloorKernel::configure(), ClCopyKernel::configure(), ClMatMulLowpNativeMMULKernel::configure(), ClPool2dKernel::configure(), ClPool3dKernel::configure(), CPPDetectionOutputLayer::configure(), ClPermuteKernel::configure(), ClActivationKernel::configure(), CpuConvertFullyConnectedWeightsKernel::configure(), ClMatMulNativeKernel::configure(), CpuSoftmaxKernel::configure(), CpuConcatenate::configure(), CLStridedSliceKernel::configure(), ClConvertFullyConnectedWeightsKernel::configure(), CpuActivationKernel::configure(), ClMatMulLowpNativeKernel::configure(), CpuGemmLowpMatrixAReductionKernel::configure(), NETileKernel::configure(), NEDepthToSpaceLayerKernel::configure(), ClConcatenate::configure(), NEChannelShuffleLayerKernel::configure(), NEReverseKernel::configure(), CpuDirectConv2dOutputStageKernel::configure(), CpuMaxUnpoolingLayerKernel::configure(), NEComputeAllAnchorsKernel::configure(), NEReorgLayerKernel::configure(), CPPTopKVKernel::configure(), NESpaceToDepthLayerKernel::configure(), CpuDirectConv2dKernel::configure(), CpuElementwiseUnaryKernel::configure(), CLInstanceNormalizationLayerKernel::configure(), ClGemmMatrixMultiplyNativeKernel::configure(), CLBitwiseKernel::configure(), CLMaxUnpoolingLayerKernel::configure(), ClWinogradFilterTransformKernel::configure(), ClWinogradInputTransformKernel::configure(), CpuPool3dKernel::configure(), NEQLSTMLayerNormalizationKernel::configure(), ClGemmLowpQuantizeDownInt32ScaleByFixedPointKernel::configure(), CPPPermuteKernel::configure(), ClGemmMatrixMultiplyReshapedOnlyRhsMMULKernel::configure(), ClIndirectConv2dAddressPrecalculationKernel::configure(), CLSelectKernel::configure(), CpuGemmInterleave4x4Kernel::configure(), NENormalizationLayerKernel::configure(), ClIndirectConv2dKernel::configure(), ClWinogradOutputTransformKernel::configure(), CLComputeAllAnchorsKernel::configure(), ClGemmLowpQuantizeDownInt32ScaleByFloatKernel::configure(), ClGemmLowpQuantizeDownInt32ScaleKernel::configure(), NEFlattenLayer::configure(), NEPadLayerKernel::configure(), NERangeKernel::configure(), CLFFTScaleKernel::configure(), CLSpaceToDepthLayerKernel::configure(), CLDepthToSpaceLayerKernel::configure(), NEBoundingBoxTransformKernel::configure(), CPPDetectionPostProcessLayer::configure(), NEFFTRadixStageKernel::configure(), NEROIPoolingLayerKernel::configure(), CLTileKernel::configure(), CPPNonMaximumSuppressionKernel::configure(), CpuGemmLowpQuantizeDownInt32ScaleKernel::configure(), NEReductionOperationKernel::configure(), NEStackLayerKernel::configure(), CpuDirectConv3dKernel::configure(), CLReorgLayerKernel::configure(), NEFuseBatchNormalizationKernel::configure(), NESelectKernel::configure(), ClGemmLowpOffsetContributionOutputStageKernel::configure(), CpuCol2ImKernel::configure(), CpuDepthwiseConv2dNativeKernel::configure(), CLMeanStdDevNormalizationKernel::configure(), CpuGemmLowpQuantizeDownInt32ToInt16ScaleByFixedPointKernel::configure(), CpuDepthwiseConv2dAssemblyWrapperKernel::configure(), CpuPool2dAssemblyWrapperKernel::configure(), NEROIAlignLayerKernel::configure(), CLNormalizePlanarYUVLayerKernel::configure(), CpuGemmMatrixMultiplyKernel::configure(), NEGatherKernel::configure(), CLReductionOperationKernel::configure(), CLReverseKernel::configure(), NEBatchToSpaceLayerKernel::configure(), CpuGemmLowpQuantizeDownInt32ToInt8ScaleByFixedPointKernel::configure(), CpuGemmLowpQuantizeDownInt32ToUint8ScaleByFixedPointKernel::configure(), NEReduceMean::configure(), ClDirectConv2dKernel::configure(), NEBatchNormalizationLayerKernel::configure(), NESpaceToBatchLayerKernel::configure(), CLL2NormalizeLayerKernel::configure(), CLPadLayerKernel::configure(), CpuWeightsReshapeKernel::configure(), ClMatMulNativeMMULKernel::configure(), CLArgMinMaxLayerKernel::configure(), CLFlattenLayer::configure(), ClMulKernel::configure(), CLReduceMean::configure(), CLBoundingBoxTransformKernel::configure(), CLDepthwiseConvolutionLayerNativeKernel::configure(), ClGemmMatrixMultiplyReshapedOnlyRhsKernel::configure(), ClWeightsReshapeKernel::configure(), CLROIPoolingLayerKernel::configure(), NEReductionOperation::configure(), CLROIAlignLayerKernel::configure(), CpuGemmTranspose1xWKernel::configure(), ClGemmLowpMatrixAReductionKernel::configure(), CpuIm2ColKernel::configure(), NEPadLayer::configure(), ClGemmMatrixMultiplyReshapedKernel::configure(), CpuGemmLowpOffsetContributionOutputStageKernel::configure(), CLFuseBatchNormalizationKernel::configure(), CLBatchNormalizationLayerKernel::configure(), CLArgMinMaxLayer::configure(), CLReductionOperation::configure(), CLBatchToSpaceLayerKernel::configure(), NEFFTConvolutionLayer::configure(), CLSpaceToBatchLayerKernel::configure(), NEGenerateProposalsLayer::configure(), NELSTMLayerQuantized::configure(), CLCropResize::configure(), CLComputeMeanVariance::configure(), ClComplexMulKernel::configure(), ClGemmLowpMatrixBReductionKernel::configure(), NEDeconvolutionLayer::configure(), CpuGemmLowpMatrixBReductionKernel::configure(), CLFFTConvolutionLayer::configure(), CLGenerateProposalsLayer::configure(), CLDirectDeconvolutionLayer::configure(), CLLSTMLayerQuantized::configure(), CpuComplexMulKernel::configure(), GpuOutput::create_op(), GpuSigmoid::create_op(), GpuTanh::create_op(), GpuClamp::create_op(), GpuSoftmax::create_op(), GpuReshape::create_op(), GpuCast::create_op(), GpuOutput::is_supported_op(), GpuSoftmax::is_supported_op(), CpuMatMul::validate(), ClGemmLowpMatrixMultiplyCore::validate(), CpuGemm::validate(), ClGemmConv2d::validate(), CpuGemmLowpMatrixMultiplyCore::validate(), GpuOutput::validate_op(), GpuTanh::validate_op(), GpuSigmoid::validate_op(), GpuReshape::validate_op(), GpuCast::validate_op(), GpuClamp::validate_op(), and GpuSoftmax::validate_op().
|
inline |
Auto initialize the tensor info using another tensor info.
(COMPMID-6012) This method should remain in sync with the fields of ITensorInfo that have setters.
Definition at line 72 of file AutoConfiguration.h.
References ITensorInfo::are_values_constant(), ITensorInfo::data_layout(), ITensorInfo::data_type(), ITensorInfo::num_channels(), ITensorInfo::quantization_info(), ITensorInfo::set_are_values_constant(), ITensorInfo::set_data_layout(), ITensorInfo::set_data_type(), ITensorInfo::set_num_channels(), ITensorInfo::set_quantization_info(), ITensorInfo::set_tensor_shape(), ITensorInfo::tensor_shape(), and TensorShape::total_size().
|
inline |
Definition at line 1656 of file Types.h.
Referenced by CpuGemmConv2d::configure(), CpuGemm::validate(), and CpuGemmConv2d::validate().
| std::string arm_compute::build_information | ( | ) |
Returns the arm_compute library build information.
Contains the version number and the build options used to build the library
Referenced by main().
| Window arm_compute::calculate_max_enlarged_window | ( | const ValidRegion & | valid_region, |
| const Steps & | steps, | ||
| BorderSize | border_size | ||
| ) |
Definition at line 147 of file WindowHelpers.cpp.
References ValidRegion::anchor, BorderSize::bottom, ceil_to_multiple(), BorderSize::left, Dimensions< T >::num_dimensions(), Dimensions< int >::num_max_dimensions, BorderSize::right, Window::set(), arm_compute::test::validation::shape, ValidRegion::shape, BorderSize::top, and arm_compute::test::validation::valid_region.
| Window arm_compute::calculate_max_window | ( | const TensorShape & | shape, |
| const Steps & | steps, | ||
| bool | skip_border, | ||
| BorderSize | border_size | ||
| ) |
Definition at line 90 of file WindowHelpers.cpp.
References BorderSize::bottom, ceil_to_multiple(), BorderSize::left, Dimensions< int >::num_max_dimensions, BorderSize::right, Window::set(), arm_compute::test::validation::shape, and BorderSize::top.
| Window arm_compute::calculate_max_window | ( | const ValidRegion & | valid_region, |
| const Steps & | steps, | ||
| bool | skip_border, | ||
| BorderSize | border_size | ||
| ) |
Definition at line 29 of file WindowHelpers.cpp.
References ValidRegion::anchor, BorderSize::bottom, ceil_to_multiple(), BorderSize::left, Dimensions< T >::num_dimensions(), Dimensions< int >::num_max_dimensions, BorderSize::right, Window::set(), arm_compute::test::validation::shape, ValidRegion::shape, BorderSize::top, and arm_compute::test::validation::valid_region.
Referenced by CpuDequantizeKernel::configure(), CpuReshapeKernel::configure(), CpuTransposeKernel::configure(), ClTransposedConvolutionKernel::configure(), CpuFillKernel::configure(), ClReshapeKernel::configure(), ClTransposeKernel::configure(), ClDequantizeKernel::configure(), ClFloorKernel::configure(), CpuConcatenateBatchKernel::configure(), CpuFloorKernel::configure(), CpuPermuteKernel::configure(), ClCopyKernel::configure(), ClFillKernel::configure(), ClElementWiseUnaryKernel::configure(), CpuConcatenateWidthKernel::configure(), NELogicalKernel::configure(), CpuConcatenateHeightKernel::configure(), ClWidthConcatenate2TensorsKernel::configure(), ClPool2dKernel::configure(), ClPool3dKernel::configure(), ClHeightConcatenateKernel::configure(), ClQuantizeKernel::configure(), ClScaleKernel::configure(), ClWidthConcatenateKernel::configure(), ClPermuteKernel::configure(), ClWidthConcatenate4TensorsKernel::configure(), ClActivationKernel::configure(), ClMatMulNativeKernel::configure(), CpuConvertFullyConnectedWeightsKernel::configure(), ClCropKernel::configure(), CLStridedSliceKernel::configure(), CpuSoftmaxKernel::configure(), ClBatchConcatenateKernel::configure(), ClDepthConcatenateKernel::configure(), CpuConcatenateDepthKernel::configure(), ClMatMulLowpNativeKernel::configure(), CpuPool2dKernel::configure(), ClConvertFullyConnectedWeightsKernel::configure(), CpuGemmLowpMatrixAReductionKernel::configure(), ICLSimpleKernel::configure(), NETileKernel::configure(), NEChannelShuffleLayerKernel::configure(), CpuDirectConv2dOutputStageKernel::configure(), NEDepthToSpaceLayerKernel::configure(), NEPriorBoxLayerKernel::configure(), NEReverseKernel::configure(), CpuGemmLowpMatrixMultiplyKernel::configure(), CpuMaxUnpoolingLayerKernel::configure(), NEComputeAllAnchorsKernel::configure(), NEReorgLayerKernel::configure(), NESpaceToDepthLayerKernel::configure(), CPPUpsampleKernel::configure(), NEBitwiseNotKernel::configure(), CLBitwiseKernel::configure(), CLInstanceNormalizationLayerKernel::configure(), CLMaxUnpoolingLayerKernel::configure(), CPPPermuteKernel::configure(), ClGemmLowpQuantizeDownInt32ScaleByFixedPointKernel::configure(), ClIndirectConv2dAddressPrecalculationKernel::configure(), NEBatchToSpaceLayerKernel::configure(), NEBitwiseAndKernel::configure(), NEBitwiseOrKernel::configure(), NEBitwiseXorKernel::configure(), CpuPool3dKernel::configure(), NESpaceToBatchLayerKernel::configure(), ClIndirectConv2dKernel::configure(), CpuGemmInterleave4x4Kernel::configure(), CLSelectKernel::configure(), NENormalizationLayerKernel::configure(), ClGemmLowpQuantizeDownInt32ScaleByFloatKernel::configure(), ClGemmLowpQuantizeDownInt32ScaleKernel::configure(), CLComputeAllAnchorsKernel::configure(), CLDeconvolutionLayerUpsampleKernel::configure(), CLDepthToSpaceLayerKernel::configure(), CLFFTScaleKernel::configure(), CpuGemmMatrixAdditionKernel::configure(), NEPadLayerKernel::configure(), NERangeKernel::configure(), ClSoftmaxKernel::configure(), CLSpaceToDepthLayerKernel::configure(), CPPBoxWithNonMaximaSuppressionLimitKernel::configure(), CPPNonMaximumSuppressionKernel::configure(), NEBoundingBoxTransformKernel::configure(), CLSpaceToBatchLayerKernel::configure(), CLTileKernel::configure(), CpuAddMulAddKernel::configure(), CpuDirectConv3dKernel::configure(), CpuGemmLowpQuantizeDownInt32ScaleKernel::configure(), NEReductionOperationKernel::configure(), ClCastKernel::configure(), NESelectKernel::configure(), CLMeanStdDevNormalizationKernel::configure(), ClGemmLowpOffsetContributionOutputStageKernel::configure(), CpuDepthwiseConv2dNativeKernel::configure(), CpuCol2ImKernel::configure(), CLBatchToSpaceLayerKernel::configure(), CLReorgLayerKernel::configure(), NEFuseBatchNormalizationKernel::configure(), ClGemmLowpOffsetContributionKernel::configure(), CpuCastKernel::configure(), CpuGemmLowpOffsetContributionKernel::configure(), CpuGemmLowpQuantizeDownInt32ToInt16ScaleByFixedPointKernel::configure(), CLNormalizePlanarYUVLayerKernel::configure(), CpuDepthwiseConv2dAssemblyWrapperKernel::configure(), CpuPool2dAssemblyWrapperKernel::configure(), CLRangeKernel::configure(), NEGatherKernel::configure(), CLReductionOperationKernel::configure(), CpuGemmMatrixMultiplyKernel::configure(), CLReverseKernel::configure(), CpuScaleKernel::configure(), CpuGemmLowpQuantizeDownInt32ToUint8ScaleByFixedPointKernel::configure(), CpuGemmLowpQuantizeDownInt32ToInt8ScaleByFixedPointKernel::configure(), ClDirectConv2dKernel::configure(), NEBatchNormalizationLayerKernel::configure(), ClDirectConv3dKernel::configure(), CLL2NormalizeLayerKernel::configure(), CpuWeightsReshapeKernel::configure(), CLPadLayerKernel::configure(), ClMulKernel::configure(), CLArgMinMaxLayerKernel::configure(), CLBoundingBoxTransformKernel::configure(), CLDepthwiseConvolutionLayerNativeKernel::configure(), ClWeightsReshapeKernel::configure(), CLROIPoolingLayerKernel::configure(), ClGemmLowpMatrixAReductionKernel::configure(), CpuGemmTranspose1xWKernel::configure(), CLROIAlignLayerKernel::configure(), CpuIm2ColKernel::configure(), CpuGemmLowpOffsetContributionOutputStageKernel::configure(), CLFuseBatchNormalizationKernel::configure(), CLBatchNormalizationLayerKernel::configure(), CLCropResize::configure(), CLComputeMeanVariance::configure(), ClComplexMulKernel::configure(), ClGemmLowpMatrixBReductionKernel::configure(), CpuComplexMulKernel::configure(), NECropKernel::configure_output_shape(), arm_compute::cpu::kernels::convolve_nchw(), arm_compute::cpu::kernels::convolve_nhwc(), arm_compute::cpu::directconv3d_float_neon_ndhwc(), arm_compute::cpu::directconv3d_quantized_neon_ndhwc(), GpuCkwElementwiseBinary::get_window(), GpuCkwActivation::get_window(), GpuCkwCast::get_window(), GpuCkwResize::get_window(), GpuCkwPool2d::get_window(), GpuCkwDepthwiseConv2d::get_window(), GpuCkwDirectConv2d::get_window(), GpuCkwMatMul::get_window(), CpuReshapeKernel::prepare(), NEStackLayerKernel::prepare(), arm_compute::cpu::kernels::validate_and_configure_window(), and arm_compute::opencl::kernels::validate_and_configure_window_for_mmul_kernels().
| Window arm_compute::calculate_max_window_horizontal | ( | const ValidRegion & | valid_region, |
| const Steps & | steps, | ||
| bool | skip_border, | ||
| BorderSize | border_size | ||
| ) |
Definition at line 198 of file WindowHelpers.cpp.
References ValidRegion::anchor, BorderSize::bottom, ceil_to_multiple(), BorderSize::left, Dimensions< T >::num_dimensions(), Dimensions< int >::num_max_dimensions, BorderSize::right, Window::set(), arm_compute::test::validation::shape, ValidRegion::shape, BorderSize::top, and arm_compute::test::validation::valid_region.
Referenced by CpuGemmLowpMatrixBReductionKernel::configure().
| PadStrideInfo calculate_same_pad | ( | TensorShape | input_shape, |
| TensorShape | weights_shape, | ||
| PadStrideInfo | conv_info, | ||
| DataLayout | data_layout = DataLayout::NCHW, |
||
| const Size2D & | dilation = Size2D(1u, 1u), |
||
| const DimensionRoundingType & | rounding_type = DimensionRoundingType::FLOOR |
||
| ) |
Calculate padding requirements in case of SAME padding.
| [in] | input_shape | Input shape |
| [in] | weights_shape | Weights shape |
| [in] | conv_info | Convolution information (containing strides) |
| [in] | data_layout | (Optional) Data layout of the input and weights tensor |
| [in] | dilation | (Optional) Dilation factor used in the convolution. |
| [in] | rounding_type | (Optional) Dimension rounding type when down-scaling. |
Definition at line 218 of file Utils.cpp.
References ARM_COMPUTE_ERROR_ON, ARM_COMPUTE_ERROR_ON_MSG, ARM_COMPUTE_UNUSED, CEIL, arm_compute::test::validation::conv_info, arm_compute::cpu::data_layout, get_data_layout_dimension_index(), HEIGHT, arm_compute::cpu::height_idx, arm_compute::test::validation::input_shape, scaled_dimensions(), WIDTH, arm_compute::cpu::width_idx, Size2D::x(), and Size2D::y().
Referenced by arm_compute::utils::calculate_convolution_padding().
| std::pair<Window, size_t> arm_compute::calculate_squashed_or_max_window | ( | const ITensorInfo & | src | ) |
Definition at line 307 of file WindowHelpers.cpp.
References Window::DimX, Window::DimY, Dimensions< int >::num_max_dimensions, Window::set(), arm_compute::test::validation::shape, and arm_compute::test::validation::src.
| std::pair<Window, size_t> arm_compute::calculate_squashed_or_max_window | ( | const ITensorInfo & | src0, |
| const ITensorInfo & | src1 | ||
| ) |
Definition at line 256 of file WindowHelpers.cpp.
References Window::DimX, Window::DimY, ITensorInfo::element_size(), ITensorInfo::num_dimensions(), Dimensions< int >::num_max_dimensions, Window::set(), ITensorInfo::strides_in_bytes(), and ITensorInfo::tensor_shape().
Referenced by CpuQuantizeKernel::configure(), CpuActivationKernel::configure(), CpuSubKernel::configure(), CpuAddKernel::configure(), CpuMulKernel::configure(), and CpuReshapeKernel::prepare().
|
inline |
Calculate subsampled shape for a given format and channel.
| [in] | shape | Shape of the tensor to calculate the extracted channel. |
| [in] | format | Format of the tensor. |
| [in] | channel | Channel to create tensor shape to be extracted. |
Definition at line 400 of file Validate.h.
References update_supported_ops::format, has_format_horizontal_subsampling(), has_format_vertical_subsampling(), arm_compute::test::validation::shape, U, arm_compute::utils::cast::U, UNKNOWN, and V.
Referenced by error_on_tensors_not_subsampled().
| ValidRegion calculate_valid_region_scale | ( | const ITensorInfo & | src_info, |
| const TensorShape & | dst_shape, | ||
| InterpolationPolicy | interpolate_policy, | ||
| SamplingPolicy | sampling_policy, | ||
| bool | border_undefined | ||
| ) |
Helper function to calculate the Valid Region for Scale.
| [in] | src_info | Input tensor info used to check. |
| [in] | dst_shape | Shape of the output. |
| [in] | interpolate_policy | Interpolation policy. |
| [in] | sampling_policy | Sampling policy. |
| [in] | border_undefined | True if the border is undefined. |
Definition at line 28 of file Helpers.cpp.
References ValidRegion::anchor, AREA, ARM_COMPUTE_ERROR, BILINEAR, CENTER, arm_compute::cpu::data_layout, TensorInfo::data_layout(), arm_compute::test::validation::dst_shape, get_data_layout_dimension_index(), HEIGHT, arm_compute::test::validation::idx_height, arm_compute::test::validation::idx_width, NEAREST_NEIGHBOR, Dimensions< T >::num_dimensions(), arm_compute::test::validation::sampling_policy, arm_compute::test::validation::scale_x, arm_compute::test::validation::scale_y, Dimensions< T >::set(), TensorShape::set(), ValidRegion::shape, arm_compute::test::validation::src_info, TensorInfo::tensor_shape(), arm_compute::test::validation::valid_region, TensorInfo::valid_region(), and WIDTH.
Referenced by arm_compute::test::validation::FIXTURE_DATA_TEST_CASE().
|
inline |
Computes the smallest number larger or equal to value that is a multiple of divisor.
| [in] | value | Lower bound value |
| [in] | divisor | Value to compute multiple of. |
Definition at line 50 of file Math.h.
References ARM_COMPUTE_ERROR_ON, and DIV_CEIL().
Referenced by calculate_max_enlarged_window(), calculate_max_window(), calculate_max_window_horizontal(), ClDequantizeKernel::configure(), ClCopyKernel::configure(), ClElementWiseUnaryKernel::configure(), ClFillKernel::configure(), ClQuantizeKernel::configure(), ClCropKernel::configure(), CLStridedSliceKernel::configure(), CLTileKernel::configure(), CLPadLayerKernel::configure(), GpuCkwDirectConv2d::get_window(), arm_compute::opencl::kernels::gemm::is_mmul_kernel_preferred(), CpuGemmLowpMatrixMultiplyKernel::run_op(), ClCropKernel::run_op(), ClDirectConv3dKernel::run_op(), ClIm2ColKernel::run_op(), Window::scale(), arm_compute::opencl::kernels::validate_and_configure_window_for_mmul_kernels(), and arm_compute::cpu::vector_matrix_multiply_f32().
Return the channel index of a given channel given an input format.
| [in] | format | Input format |
| [in] | channel | Input channel |
Definition at line 143 of file FormatUtils.h.
References A, ARM_COMPUTE_ERROR, B, update_supported_ops::format, G, IYUV, NV12, NV21, R, RGB888, RGBA8888, U, UYVY422, V, Y, YUV444, and YUYV422.
| bool arm_compute::check_value_range | ( | T | val, |
| DataType | dt, | ||
| QuantizationInfo | qinfo = QuantizationInfo() |
||
| ) |
Returns true if the value can be represented by the given data type.
| [in] | val | value to be checked |
| [in] | dt | data type that is checked |
| [in] | qinfo | (Optional) quantization info if the data type is QASYMM8 |
Definition at line 439 of file DataTypeUtils.h.
References ARM_COMPUTE_ERROR, BFLOAT16, dequantize_qasymm8(), dt, F16, F32, bfloat16::lowest(), arm_compute::support::cpp11::lowest(), bfloat16::max(), QASYMM8, arm_compute::test::validation::qinfo, S16, S32, S8, U16, U32, and U8.
| bool cl_winograd_convolution_layer_supported | ( | const Size2D & | output_tile, |
| const Size2D & | kernel_size, | ||
| DataLayout | data_layout | ||
| ) |
This function checks if the Winograd configuration (defined through the output tile, kernel size and the data layout) is supported on OpenCL.
| [in] | output_tile | Output tile for the Winograd filtering algorithm |
| [in] | kernel_size | Kernel size for the Winograd filtering algorithm |
| [in] | data_layout | Data layout of the input tensor |
Definition at line 292 of file CLHelpers.cpp.
References ARM_COMPUTE_ERROR_ON, arm_compute::cpu::data_layout, Size2D::height, NCHW, UNKNOWN, and Size2D::width.
| void arm_compute::colorconvert_iyuv_to_nv12 | ( | const void *__restrict | input, |
| void *__restrict | output, | ||
| const Window & | win | ||
| ) |
Convert IYUV to NV12.
| [in] | input | Input IYUV data buffer. |
| [out] | output | Output NV12 buffer. |
| [in] | win | Window for iterating the buffers. |
Definition at line 717 of file NEColorConvertHelper.inl.
References ARM_COMPUTE_ERROR_ON, Window::DimX, Window::DimY, Window::Dimension::end(), execute_window_loop(), arm_compute::test::validation::input, Iterator::ptr(), Window::set(), Window::Dimension::start(), Window::Dimension::step(), Window::validate(), Window::x(), and Window::y().
| void arm_compute::colorconvert_iyuv_to_rgb | ( | const void *__restrict | input, |
| void *__restrict | output, | ||
| const Window & | win | ||
| ) |
Convert IYUV to RGB.
| [in] | input | Input IYUV data buffer. |
| [out] | output | Output RGB buffer. |
| [in] | win | Window for iterating the buffers. |
Definition at line 562 of file NEColorConvertHelper.inl.
References ARM_COMPUTE_ERROR_ON, convert_uint8x16_to_float32x4x4(), Window::DimX, Window::DimY, Window::Dimension::end(), execute_window_loop(), ITensor::info(), arm_compute::test::validation::input, Iterator::ptr(), Window::set(), Window::Dimension::start(), Window::Dimension::step(), ITensorInfo::strides_in_bytes(), Window::validate(), Window::x(), Dimensions< T >::y(), Window::y(), and arm_compute::test::colorconvert_helper::detail::yuyv_to_rgb_calculation().
| void arm_compute::colorconvert_iyuv_to_yuv4 | ( | const void *__restrict | input, |
| void *__restrict | output, | ||
| const Window & | win | ||
| ) |
Convert IYUV to YUV4.
| [in] | input | Input IYUV data buffer. |
| [out] | output | Output YUV4 buffer. |
| [in] | win | Window for iterating the buffers. |
Definition at line 940 of file NEColorConvertHelper.inl.
References ARM_COMPUTE_ERROR_ON, Window::DimX, Window::DimY, Window::Dimension::end(), execute_window_loop(), arm_compute::test::validation::input, Iterator::ptr(), Window::set(), Window::Dimension::start(), Window::Dimension::step(), Window::validate(), Window::x(), and Window::y().
| void arm_compute::colorconvert_nv12_to_iyuv | ( | const void *__restrict | input, |
| void *__restrict | output, | ||
| const Window & | win | ||
| ) |
Convert NV12 to IYUV.
| [in] | input | Input NV12 data buffer. |
| [out] | output | Output IYUV buffer. |
| [in] | win | Window for iterating the buffers. |
Definition at line 767 of file NEColorConvertHelper.inl.
References ARM_COMPUTE_ERROR_ON, Window::DimX, Window::DimY, Window::Dimension::end(), execute_window_loop(), arm_compute::test::validation::input, Iterator::ptr(), Window::set(), Window::Dimension::start(), Window::Dimension::step(), Window::validate(), Window::x(), and Window::y().
| void arm_compute::colorconvert_nv12_to_rgb | ( | const void *__restrict | input, |
| void *__restrict | output, | ||
| const Window & | win | ||
| ) |
Convert NV12 to RGB.
| [in] | input | Input NV12 data buffer. |
| [out] | output | Output RGB buffer. |
| [in] | win | Window for iterating the buffers. |
Definition at line 490 of file NEColorConvertHelper.inl.
References ARM_COMPUTE_ERROR_ON, convert_uint8x16_to_float32x4x4(), Window::DimX, Window::DimY, Window::Dimension::end(), execute_window_loop(), ITensor::info(), arm_compute::test::validation::input, Iterator::ptr(), Window::set(), Window::Dimension::start(), Window::Dimension::step(), ITensorInfo::strides_in_bytes(), Window::validate(), Window::x(), Dimensions< T >::y(), Window::y(), and arm_compute::test::colorconvert_helper::detail::yuyv_to_rgb_calculation().
| void arm_compute::colorconvert_nv12_to_yuv4 | ( | const void *__restrict | input, |
| void *__restrict | output, | ||
| const Window & | win | ||
| ) |
Convert NV12 to YUV4.
| [in] | input | Input NV12 data buffer. |
| [out] | output | Output YUV4 buffer. |
| [in] | win | Window for iterating the buffers. |
Definition at line 880 of file NEColorConvertHelper.inl.
References ARM_COMPUTE_ERROR_ON, Window::DimX, Window::DimY, Window::Dimension::end(), execute_window_loop(), arm_compute::test::validation::input, Iterator::ptr(), Window::set(), Window::Dimension::start(), Window::Dimension::step(), Window::validate(), Window::x(), and Window::y().
| void arm_compute::colorconvert_rgb_to_iyuv | ( | const void *__restrict | input, |
| void *__restrict | output, | ||
| const Window & | win | ||
| ) |
Convert RGB to IYUV.
| [in] | input | Input RGB data buffer. |
| [out] | output | Output IYUV buffer. |
| [in] | win | Window for iterating the buffers. |
Definition at line 1045 of file NEColorConvertHelper.inl.
References ARM_COMPUTE_ERROR_ON, Window::DimX, Window::DimY, Window::Dimension::end(), execute_window_loop(), arm_compute::test::validation::input, Iterator::ptr(), Window::set(), Window::Dimension::start(), Window::Dimension::step(), Window::validate(), Window::x(), and Window::y().
| void arm_compute::colorconvert_rgb_to_nv12 | ( | const void *__restrict | input, |
| void *__restrict | output, | ||
| const Window & | win | ||
| ) |
Convert RGB to NV12.
| [in] | input | Input RGB data buffer. |
| [out] | output | Output NV12 buffer. |
| [in] | win | Window for iterating the buffers. |
Definition at line 1001 of file NEColorConvertHelper.inl.
References ARM_COMPUTE_ERROR_ON, Window::DimX, Window::DimY, Window::Dimension::end(), execute_window_loop(), arm_compute::test::validation::input, Iterator::ptr(), Window::set(), Window::Dimension::start(), Window::Dimension::step(), Window::validate(), Window::x(), and Window::y().
| void arm_compute::colorconvert_rgb_to_rgbx | ( | const void *__restrict | input, |
| void *__restrict | output, | ||
| const Window & | win | ||
| ) |
Convert RGB to RGBX.
| [in] | input | Input RGB data buffer. |
| [out] | output | Output RGBX buffer. |
| [in] | win | Window for iterating the buffers. |
Definition at line 344 of file NEColorConvertHelper.inl.
References ARM_COMPUTE_ERROR_ON, execute_window_loop(), arm_compute::test::validation::input, and Iterator::ptr().
| void arm_compute::colorconvert_rgb_to_u8 | ( | const void *__restrict | input, |
| void *__restrict | output, | ||
| const Window & | win | ||
| ) |
Convert RGB to U8.
| [in] | input | Input RGB data buffer. |
| [out] | output | Output U8 buffer. |
| [in] | win | Window for iterating the buffers. |
Definition at line 377 of file NEColorConvertHelper.inl.
References ARM_COMPUTE_ERROR_ON, execute_window_loop(), arm_compute::test::validation::input, and Iterator::ptr().
| void arm_compute::colorconvert_rgb_to_yuv4 | ( | const void *__restrict | input, |
| void *__restrict | output, | ||
| const Window & | win | ||
| ) |
Convert RGB to YUV4.
| [in] | input | Input RGB data buffer. |
| [out] | output | Output YUV4 buffer. |
| [in] | win | Window for iterating the buffers. |
Definition at line 1091 of file NEColorConvertHelper.inl.
References ARM_COMPUTE_ERROR_ON, execute_window_loop(), arm_compute::test::validation::input, Iterator::ptr(), and Window::validate().
| void arm_compute::colorconvert_rgbx_to_rgb | ( | const void * | input, |
| void * | output, | ||
| const Window & | win | ||
| ) |
Convert RGBX to RGB.
| [in] | input | Input RGBX data buffer. |
| [out] | output | Output RGB buffer. |
| [in] | win | Window for iterating the buffers. |
Definition at line 407 of file NEColorConvertHelper.inl.
References ARM_COMPUTE_ERROR_ON, execute_window_loop(), arm_compute::test::validation::input, and Iterator::ptr().
| void arm_compute::colorconvert_yuyv_to_iyuv | ( | const void *__restrict | input, |
| void *__restrict | output, | ||
| const Window & | win | ||
| ) |
Convert YUYV to IYUV.
| [in] | input | Input YUYV data buffer. |
| [out] | output | Output IYUV buffer. |
| [in] | win | Window for iterating the buffers. |
Definition at line 818 of file NEColorConvertHelper.inl.
References ARM_COMPUTE_ERROR_ON, Window::DimX, Window::DimY, Window::Dimension::end(), execute_window_loop(), arm_compute::test::validation::input, Iterator::ptr(), Window::set(), Window::Dimension::start(), Window::Dimension::step(), Window::validate(), Window::x(), and Window::y().
| void arm_compute::colorconvert_yuyv_to_nv12 | ( | const void *__restrict | input, |
| void *__restrict | output, | ||
| const Window & | win | ||
| ) |
Convert YUYV to NV12.
| [in] | input | Input YUYV data buffer. |
| [out] | output | Output NV12 buffer. |
| [in] | win | Window for iterating the buffers. |
Definition at line 660 of file NEColorConvertHelper.inl.
References ARM_COMPUTE_ERROR_ON, Window::DimX, Window::DimY, Window::Dimension::end(), execute_window_loop(), arm_compute::test::validation::input, Iterator::ptr(), Window::set(), Window::Dimension::start(), Window::Dimension::step(), Window::validate(), Window::x(), and Window::y().
| void arm_compute::colorconvert_yuyv_to_rgb | ( | const void *__restrict | input, |
| void *__restrict | output, | ||
| const Window & | win | ||
| ) |
Convert YUYV to RGB.
| [in] | input | Input YUYV data buffer. |
| [out] | output | Output RGB buffer. |
| [in] | win | Window for iterating the buffers. |
Definition at line 440 of file NEColorConvertHelper.inl.
References ARM_COMPUTE_ERROR_ON, convert_uint8x16_to_float32x4x4(), execute_window_loop(), arm_compute::test::validation::input, Iterator::ptr(), and arm_compute::test::colorconvert_helper::detail::yuyv_to_rgb_calculation().
| bool command_buffer_mutable_dispatch_supported | ( | const cl::Device & | device | ) |
Check whether cl_khr_command_buffer_mutable_dispatch extension is supported by the specified CL device.
| [in] | device | The CL device |
Definition at line 509 of file CLHelpers.cpp.
References device_supports_extension().
Referenced by CLCommandBuffer::create().
| bool command_buffer_supported | ( | const cl::Device & | device | ) |
Check whether cl_khr_command_buffer extension is supported by the specified CL device.
| [in] | device | The CL device |
Definition at line 504 of file CLHelpers.cpp.
References device_supports_extension().
|
inline |
Definition at line 621 of file QuantizationInfo.h.
References UniformQuantizationInfo::offset, and UniformQuantizationInfo::scale.
Referenced by CpuQuantizeKernel::configure(), and CLROIPoolingLayerKernel::configure().
|
inline |
Create a strides object based on the tensor dimensions.
| [in] | info | Tensor info object used to compute the strides. |
Definition at line 63 of file Utils.h.
References compute_strides(), and arm_compute::test::validation::info.
|
inline |
Create a strides object based on the provided strides and the tensor dimensions.
| [in] | info | Tensor info object providing the shape of the tensor for unspecified strides. |
| [in] | stride_x | Stride to be used in X dimension (in bytes). |
| [in] | fixed_strides | Strides to be used in higher dimensions starting at Y (in bytes). |
Definition at line 41 of file Utils.h.
References arm_compute::test::validation::info, Dimensions< T >::set(), and arm_compute::test::validation::shape.
Referenced by compute_strides(), and TensorInfo::set_tensor_shape().
|
inline |
Calculate the number of output tiles required by Winograd Convolution layer.
This utility function can be used by the Winograd input transform to know the number of tiles on the x and y direction
| [in] | in_dims | Spatial dimensions of the input tensor of convolution layer |
| [in] | kernel_size | Kernel size |
| [in] | output_tile_size | Size of a single output tile |
| [in] | conv_info | Convolution info (i.e. pad, stride,...) |
Definition at line 250 of file Helpers.h.
References arm_compute::test::validation::conv_info, Size2D::height, and Size2D::width.
Referenced by arm_compute::misc::shape_calculator::compute_winograd_input_transform_shape(), ClWinogradInputTransformKernel::configure(), ClWinogradOutputTransformKernel::configure(), arm_compute::test::validation::reference::winograd_input_transform(), and arm_compute::test::validation::reference::winograd_output_transform().
|
inline |
Converts from two float32x4x3_t to just one uint8x8x3_t.
| [in] | in1 | First input vector of float to be converted |
| [in] | in2 | Second input vector of float to be converted |
| [out] | out | Converted output vector uint8 to store the result |
Definition at line 488 of file NEMath.inl.
|
inline |
Converts from float32x4x4_t to just one int8x16_t.
| [in] | in | Vector of float to be converted |
| [out] | out | Converted vector of uint8 to store the result |
Definition at line 502 of file NEMath.inl.
Referenced by convert_float_to_int< float32x4x4_t, int8x16_t >().
|
inline |
Converts from two float32x4x4_t to just one uint8x16_t.
| [in] | in | Vector of float to be converted |
| [out] | out | Converted vector of uint8 to store the result |
Definition at line 495 of file NEMath.inl.
Referenced by convert_float_to_int< float32x4x4_t, uint8x16_t >().
| int_vec_type arm_compute::convert_float_to_int | ( | const float_vec_type & | in | ) |
Converts from float vector to integer vector.
| [in] | in | Float vector to converted |
|
inline |
Definition at line 524 of file NEMath.inl.
References convert_float32x4x4_to_int8x16().
|
inline |
Definition at line 510 of file NEMath.inl.
References convert_float32x4x4_to_uint8x16().
|
inline |
Converts from int8x16 to float32x4x4_t.
| [in] | in | Vector of int8 to be converted |
Definition at line 462 of file NEMath.inl.
Referenced by convert_int_to_float< float32x4x4_t, int8x16_t >(), and convert_to_float32x4x4().
| float_vec_type arm_compute::convert_int_to_float | ( | const int_vec_type & | in | ) |
Converts from integer vector to float vector.
| [in] | in | Integer vector to converted |
|
inline |
Definition at line 532 of file NEMath.inl.
References convert_int8x16_to_float32x4x4().
|
inline |
Definition at line 518 of file NEMath.inl.
References convert_uint8x16_to_float32x4x4().
|
inline |
Convert negative coordinates to positive in the range [0, num_dims_input].
| [out] | coords | Array of coordinates to be converted. |
| [in] | max_value | Maximum value to be used when wrapping the negative values in coords |
Definition at line 287 of file Helpers.h.
References Dimensions< T >::num_dimensions(), and wrap_around().
Referenced by arm_compute::misc::shape_calculator::calculate_reduce_mean_shape(), NEReduceMean::configure(), and CLReduceMean::configure().
|
inline |
Definition at line 483 of file NEMath.inl.
References convert_int8x16_to_float32x4x4().
| float32x4x4_t arm_compute::convert_to_float32x4x4 | ( | const T & | in | ) |
Converts to float32x4x4_t from the specified templated 16 elements vectors.
| [in] | in | Vector of float to be converted |
|
inline |
Definition at line 477 of file NEMath.inl.
References convert_uint8x16_to_float32x4x4().
|
inline |
Converts from uint8x16 to float32x4x4_t.
| [in] | in | Vector of uint8 to be converted |
Definition at line 448 of file NEMath.inl.
Referenced by colorconvert_iyuv_to_rgb(), colorconvert_nv12_to_rgb(), colorconvert_yuyv_to_rgb(), convert_int_to_float< float32x4x4_t, uint8x16_t >(), and convert_to_float32x4x4().
|
inline |
Convert an offset in window steps into absolute coordinates.
| [in] | w | Window offset is related to. |
| [in] | offset | Offset inside the window expressed in number of window steps. |
Definition at line 40 of file WindowIterator.h.
References Dimensions< int >::num_max_dimensions, offset(), Dimensions< T >::set(), arm_compute::cpu::step, and arm_compute::test::validation::w.
|
inline |
Convert n-dimensional coordinates into a linear index.
| [in] | shape | Shape of the n-dimensional tensor. |
| [in] | coord | N-dimensional coordinates. |
Definition at line 183 of file Helpers.inl.
References ARM_COMPUTE_ERROR_ON_MSG, ARM_COMPUTE_UNUSED, Dimensions< T >::num_dimensions(), and arm_compute::test::validation::shape.
Referenced by arm_compute::test::validation::reference::convert_fully_connected_weights(), arm_compute::test::validation::reference::gather(), and arm_compute::test::validation::reference::winograd_input_transform().
|
inline |
Returns the suffix string of CPU kernel implementation names based on the given data type.
| [in] | data_type | The data type the CPU kernel implemetation uses |
Definition at line 505 of file DataTypeUtils.h.
References ARM_COMPUTE_ERROR, BFLOAT16, arm_compute::test::validation::data_type, F16, F32, QASYMM8, QASYMM8_SIGNED, QSYMM16, QSYMM8_PER_CHANNEL, S16, S32, and U8.
| Status create_error_msg | ( | ErrorCode | error_code, |
| const char * | func, | ||
| const char * | file, | ||
| int | line, | ||
| const char * | msg | ||
| ) |
Creates an error and the error message.
| [in] | error_code | Error code |
| [in] | func | Function in which the error occurred. |
| [in] | file | File in which the error occurred. |
| [in] | line | Line in which the error occurred. |
| [in] | msg | Message to display before abandoning. |
Definition at line 40 of file Error.cpp.
References arm_compute::support::cpp11::snprintf().
| cl::Image2D create_image2d_from_buffer | ( | const cl::Context & | ctx, |
| const cl::Buffer & | buffer, | ||
| const TensorShape & | shape2d, | ||
| DataType | data_type, | ||
| size_t | image_row_pitch, | ||
| CLImage2DType | image_type | ||
| ) |
Create a cl::Image2D object from an OpenCL buffer.
It is user responsibility to ensure the above conditions are satisfied since no checks are performed within this function
| [in] | ctx | cl::Context object |
| [in] | buffer | cl::Buffer object from which the OpenCL image2d object is created |
| [in] | shape2d | 2D tensor shape |
| [in] | data_type | DataType to use. Only supported: F32,F16 |
| [in] | image_row_pitch | Image row pitch (a.k.a. stride Y) to be used in the image2d object |
| [in] | image_type | Image 2D type (CLImage2DType) |
Definition at line 62 of file CLUtils.cpp.
References ARM_COMPUTE_ERROR, ARM_COMPUTE_ERROR_ON_MSG, ARM_COMPUTE_UNUSED, clCreateImage(), arm_compute::test::validation::data_type, F16, F32, update_supported_ops::format, CLKernelLibrary::get(), get_cl_image_pitch_alignment(), image2d_from_buffer_supported(), ReadOnly, and WriteOnly.
Referenced by create_image2d_from_tensor(), CLDepthwiseConvolutionLayerNativeKernel::run(), ClMatMulNativeKernel::run_op(), ClIndirectConv2dKernel::run_op(), ClGemmMatrixMultiplyReshapedOnlyRhsMMULKernel::run_op(), ClGemmMatrixMultiplyReshapedOnlyRhsKernel::run_op(), and ClGemmMatrixMultiplyReshapedKernel::run_op().
| cl::Image2D create_image2d_from_tensor | ( | const ICLTensor * | tensor, |
| CLImage2DType | image_type | ||
| ) |
Create a cl::Image2D object from a tensor.
| [in] | tensor | Tensor from which to construct Image 2D object |
| [in] | image_type | Image 2D type (CLImage2DType) |
Definition at line 37 of file CLUtils.cpp.
References ARM_COMPUTE_ERROR_ON_MSG, ARM_COMPUTE_ERROR_ON_NULLPTR, ARM_COMPUTE_UNUSED, CLTensor::cl_buffer(), CLKernelLibrary::context(), create_image2d_from_buffer(), CLKernelLibrary::get(), CLKernelLibrary::get_device(), CLTensor::info(), arm_compute::test::validation::info, and tensor.
Referenced by ClDirectConv2dKernel::run_op().
| 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.
| [in] | ctx | A compile context to be used to create the opencl kernel. |
| [in] | kernel_name | The kernel name. |
| [in] | build_opts | The build options to be used for the opencl kernel compilation. |
Definition at line 409 of file CLHelpers.cpp.
References CLCompileContext::create_kernel(), ClKernelLibrary::get(), kernel_name, ClKernelLibrary::kernel_path(), ClKernelLibrary::program(), and ClKernelLibrary::program_name().
Referenced by ClTransposedConvolutionKernel::configure(), ClDequantizeKernel::configure(), ClReshapeKernel::configure(), ClTransposeKernel::configure(), ClFloorKernel::configure(), ClCopyKernel::configure(), ClElementWiseUnaryKernel::configure(), ClFillKernel::configure(), ClMatMulLowpNativeMMULKernel::configure(), ClWidthConcatenate2TensorsKernel::configure(), ClPool2dKernel::configure(), ClPool3dKernel::configure(), ClHeightConcatenateKernel::configure(), ClQuantizeKernel::configure(), ClScaleKernel::configure(), ClWidthConcatenateKernel::configure(), ClActivationKernel::configure(), ClPermuteKernel::configure(), ClWidthConcatenate4TensorsKernel::configure(), ClMatMulNativeKernel::configure(), ClCropKernel::configure(), CLStridedSliceKernel::configure(), ClBatchConcatenateKernel::configure(), ClDepthConcatenateKernel::configure(), ClMatMulLowpNativeKernel::configure(), ClConvertFullyConnectedWeightsKernel::configure(), ClGemmLowpMatrixMultiplyNativeKernel::configure(), ClGemmReshapeLhsMatrixKernel::configure(), CLInstanceNormalizationLayerKernel::configure(), ClGemmMatrixMultiplyNativeKernel::configure(), CLBitwiseKernel::configure(), CLMaxUnpoolingLayerKernel::configure(), ClGemmMatrixMultiplyReshapedOnlyRhsMMULKernel::configure(), ClIndirectConv2dAddressPrecalculationKernel::configure(), ClWinogradInputTransformKernel::configure(), CLChannelShuffleLayerKernel::configure(), ClWinogradFilterTransformKernel::configure(), ClGemmLowpQuantizeDownInt32ScaleByFixedPointKernel::configure(), CLSelectKernel::configure(), ClIndirectConv2dKernel::configure(), CLComputeAllAnchorsKernel::configure(), CLDeconvolutionLayerUpsampleKernel::configure(), ClWinogradOutputTransformKernel::configure(), ClGemmLowpQuantizeDownInt32ScaleByFloatKernel::configure(), ClGemmLowpQuantizeDownInt32ScaleKernel::configure(), CLSpaceToDepthLayerKernel::configure(), CLDepthToSpaceLayerKernel::configure(), ClSoftmaxKernel::configure(), CLNormalizationLayerKernel::configure(), CLQLSTMLayerNormalizationKernel::configure(), CLFFTScaleKernel::configure(), CLGatherKernel::configure(), CLTileKernel::configure(), CLSpaceToBatchLayerKernel::configure(), ClGemmLowpMatrixMultiplyReshapedKernel::configure(), ClCastKernel::configure(), CLComparisonKernel::configure(), ClGemmLowpOffsetContributionOutputStageKernel::configure(), CLBatchToSpaceLayerKernel::configure(), ClGemmReshapeRhsMatrixKernel::configure(), CLFFTDigitReverseKernel::configure(), CLMeanStdDevNormalizationKernel::configure(), ClGemmLowpOffsetContributionKernel::configure(), CLReorgLayerKernel::configure(), CLNormalizePlanarYUVLayerKernel::configure(), CLReverseKernel::configure(), CLRangeKernel::configure(), CLReductionOperationKernel::configure(), ClDirectConv2dKernel::configure(), ClCol2ImKernel::configure(), CLFFTRadixStageKernel::configure(), ClDirectConv3dKernel::configure(), ClGemmLowpMatrixMultiplyReshapedOnlyRhsKernel::configure(), CLL2NormalizeLayerKernel::configure(), ClMatMulNativeMMULKernel::configure(), CLPadLayerKernel::configure(), CLArgMinMaxLayerKernel::configure(), ClMulKernel::configure(), ClGemmMatrixMultiplyReshapedOnlyRhsKernel::configure(), CLDepthwiseConvolutionLayerNativeKernel::configure(), CLBoundingBoxTransformKernel::configure(), CLROIPoolingLayerKernel::configure(), CLPriorBoxLayerKernel::configure(), ClWeightsReshapeKernel::configure(), CLStackLayerKernel::configure(), ClGemmLowpMatrixAReductionKernel::configure(), CLROIAlignLayerKernel::configure(), ClIm2ColKernel::configure(), CLFillBorderKernel::configure(), ClGemmMatrixMultiplyReshapedKernel::configure(), CLDeconvolutionReshapeOutputKernel::configure(), CLFuseBatchNormalizationKernel::configure(), CLBatchNormalizationLayerKernel::configure(), CLComputeMeanVariance::configure(), ClComplexMulKernel::configure(), and ClGemmLowpMatrixBReductionKernel::configure().
| cl::NDRange create_lws_hint_parallel_implementations | ( | unsigned int | input_dimension, |
| unsigned int | vector_size | ||
| ) |
Creates a suitable LWS hint object for parallel implementations.
Sets the number of WG based on the input size. If input width is smaller than 128 we can use fewer threads than 8.
| [in] | input_dimension | number of elements along the dimension to apply the parallellization |
| [in] | vector_size | size of the vector in OpenCL |
Definition at line 421 of file CLHelpers.cpp.
References arm_compute::utils::cast::U, and arm_compute::cpu::vector_size.
| std::tuple< cl::Context, cl::Device, cl_int > create_opencl_context_and_device | ( | CLBackendType | cl_backend_type | ) |
This function creates an OpenCL context and a device.
| [in] | cl_backend_type | The OpenCL backend type to use. |
Definition at line 121 of file CLHelpers.cpp.
References ARM_COMPUTE_ERROR_ON, ARM_COMPUTE_ERROR_ON_MSG, opencl_is_available(), and select_preferable_platform().
Referenced by CLRuntimeContext::CLRuntimeContext(), CLScheduler::default_init(), and main().
| WindowIterator<L> arm_compute::create_window_iterator | ( | const Window & | w, |
| const Coordinates & | start, | ||
| const Coordinates & | end, | ||
| L && | lambda_function | ||
| ) |
Create a WindowIterator object.
| [in] | w | Window to use for the iteration |
| [in] | start | Where to start iterating from (In Window coordinates) |
| [in] | end | Where to stop iterating (In Window coordinates). |
| [in] | lambda_function | Lambda function to call for every iteration between start and end. (It will be called last for end - 1) |
Definition at line 313 of file WindowIterator.h.
References arm_compute::mlgo::parser::end(), and arm_compute::test::validation::w.
| arm_compute::DataLayout data_layout_from_name | ( | const std::string & | name | ) |
Converts a string to a strong types enumeration DataLayout.
| [in] | name | String to convert |
Definition at line 32 of file TypeLoader.cpp.
References name, NCHW, NHWC, and arm_compute::utility::tolower().
Referenced by operator>>().
|
inline |
The size in bytes of the data type.
| [in] | data_type | Input data type |
Definition at line 38 of file DataTypeUtils.h.
References ARM_COMPUTE_ERROR, BFLOAT16, arm_compute::test::validation::data_type, F16, F32, F64, QASYMM16, QASYMM8, QASYMM8_SIGNED, QSYMM16, QSYMM8, QSYMM8_PER_CHANNEL, S16, S32, S64, S8, SIZET, U16, U32, U64, and U8.
Referenced by ClPermuteKernel::configure(), CLStridedSliceKernel::configure(), CLSpaceToDepthLayerKernel::configure(), CLGatherKernel::configure(), CLSpaceToBatchLayerKernel::configure(), CLTileKernel::configure(), ClCastKernel::configure(), ClWeightsReshapeKernel::configure(), CLBatchToSpaceLayerKernel::configure(), TensorInfo::element_size(), arm_compute::cpu::l2_normalize_x(), arm_compute::cpu::l2_normalize_yz(), arm_compute::cpu::matrix_matrix_multiply_f32(), CpuGemmLowpMatrixMultiplyKernel::run_op(), and arm_compute::cpu::vector_matrix_multiply_f32().
Return the data type used by a given single-planar pixel format.
| [in] | format | Input format |
Definition at line 115 of file DataTypeUtils.h.
References ARM_COMPUTE_ERROR, BFLOAT16, F16, F32, update_supported_ops::format, IYUV, NV12, NV21, RGB888, RGBA8888, S16, S32, U16, U32, U8, UNKNOWN, UV88, UYVY422, YUV444, and YUYV422.
Referenced by SimpleTensor< uint8_t >::data_type(), TensorInfo::init(), TensorInfo::init_auto_padding(), and TensorInfo::set_format().
| DataType data_type_from_name | ( | const std::string & | name | ) |
Convert a string to DataType.
| [in] | name | The name of the data type |
Definition at line 58 of file DataTypeUtils.cpp.
References ARM_COMPUTE_ERROR_VAR, F16, F32, name, QASYMM8, QASYMM8_SIGNED, and arm_compute::utility::tolower().
Referenced by operator>>().
| std::pair< unsigned int, unsigned int > deconvolution_output_dimensions | ( | unsigned int | in_width, |
| unsigned int | in_height, | ||
| unsigned int | kernel_width, | ||
| unsigned int | kernel_height, | ||
| const PadStrideInfo & | pad_stride_info | ||
| ) |
Returns expected width and height of the deconvolution's output tensor.
| [in] | in_width | Width of input tensor (Number of columns) |
| [in] | in_height | Height of input tensor (Number of rows) |
| [in] | kernel_width | Kernel width. |
| [in] | kernel_height | Kernel height. |
| [in] | pad_stride_info | Pad and stride information. |
Definition at line 266 of file Utils.cpp.
References ARM_COMPUTE_ERROR_ON, PadStrideInfo::pad_bottom(), PadStrideInfo::pad_left(), PadStrideInfo::pad_right(), PadStrideInfo::pad_top(), PadStrideInfo::stride(), and arm_compute::test::validation::w.
Referenced by DeconvolutionLayerNode::compute_output_descriptor(), ClTransposedConvolutionKernel::configure(), NEDeconvolutionLayer::configure(), CLDirectDeconvolutionLayer::configure(), NEDeconvolutionLayer::validate(), CLGEMMDeconvolutionLayer::validate(), and CLDirectDeconvolutionLayer::validate().
|
inline |
Dequantize a value given a 16-bit symmetric quantization scheme.
| [in] | value | Value to dequantize |
| [in] | scale | Scale to use for dequantization |
Definition at line 429 of file QuantizationInfo.h.
References arm_compute::test::validation::scale.
|
inline |
Dequantize a value given a 32-bit asymmetric quantization scheme.
| [in] | value | Value to dequantize |
| [in] | scale | Scale to use for dequantization |
| [in] | offset | Zero-offset to use for dequantization |
Definition at line 455 of file QuantizationInfo.h.
References offset(), and arm_compute::test::validation::scale.
|
inline |
Dequantize a value given a 8-bit symmetric quantization scheme.
| [in] | value | Value to dequantize |
| [in] | scale | Scale to use for dequantization |
Definition at line 417 of file QuantizationInfo.h.
References arm_compute::test::validation::scale.
|
inline |
Dequantize a value given a 16-bit asymmetric quantization scheme.
| [in] | value | Value to dequantize |
| [in] | scale | Scale to use for dequantization |
| [in] | offset | Zero-offset to use for dequantization |
Definition at line 442 of file QuantizationInfo.h.
References offset(), and arm_compute::test::validation::scale.
|
inline |
Dequantize a value given an 8-bit asymmetric quantization scheme.
| [in] | value | Value to dequantize |
| [in] | scale | Scale to use for dequantization |
| [in] | offset | Zero-offset to use for dequantization |
Definition at line 393 of file QuantizationInfo.h.
References offset(), and arm_compute::test::validation::scale.
|
inline |
Dequantize a value given a 16-bit asymmetric quantization scheme.
| [in] | value | Value to dequantize |
| [in] | qinfo | Quantization information to use for dequantizing |
Definition at line 561 of file QuantizationInfo.h.
References dequantize_qasymm16(), arm_compute::test::validation::qinfo, and QuantizationInfo::uniform().
|
inline |
Dequantize a value given a 16-bit asymmetric quantization scheme.
| [in] | value | Value to dequantize |
| [in] | qinfo | Quantization information to use for dequantizing |
Definition at line 537 of file QuantizationInfo.h.
References QuantizationInfo::offset(), arm_compute::test::validation::qinfo, and QuantizationInfo::scale().
Referenced by arm_compute::cpu::bounding_box_transform_qsymm16(), arm_compute::test::validation::convert_from_asymmetric(), dequantize_qasymm16(), and arm_compute::cpu::roi_align().
|
inline |
Dequantize a value given an unsigned 8-bit asymmetric quantization scheme.
| [in] | value | Value to dequantize |
| [in] | qinfo | Quantization information to use for dequantizing |
Definition at line 367 of file QuantizationInfo.h.
References Qasymm8QuantizationHelper< QUANTIZED_TYPE >::dequantize(), and arm_compute::test::validation::qinfo.
Referenced by arm_compute::cpu::bounding_box_transform_qsymm16(), check_value_range(), arm_compute::test::validation::convert_from_asymmetric(), arm_compute::scale_helpers::delta_bilinear_c1_quantized(), arm_compute::test::validation::reference::depthconcatenate_layer(), arm_compute::cpu::elementwise_op< uint8_t >(), arm_compute::cpu::elementwise_op_quantized(), arm_compute::cpu::neon_qasymm8_activation(), arm_compute::cpu::roi_align_1x1_qasymm8(), CPPDetectionPostProcessLayer::run(), CpuConcatenateHeightKernel::run_op(), CpuConcatenateWidthKernel::run_op(), and arm_compute::test::validation::reference::scale().
|
inline |
Dequantize a value given a signed 8-bit asymmetric quantization scheme.
| [in] | value | Value to dequantize |
| [in] | qinfo | Quantization information to use for dequantizing |
Definition at line 380 of file QuantizationInfo.h.
References Qasymm8QuantizationHelper< QUANTIZED_TYPE >::dequantize(), and arm_compute::test::validation::qinfo.
Referenced by arm_compute::test::validation::convert_from_asymmetric(), arm_compute::scale_helpers::delta_bilinear_c1_quantized(), arm_compute::cpu::elementwise_comp_quantized_signed(), arm_compute::cpu::elementwise_op< int8_t >(), arm_compute::cpu::elementwise_op_quantized_signed(), arm_compute::cpu::neon_qasymm8_signed_activation(), arm_compute::cpu::roi_align_1x1_qasymm8(), CPPDetectionPostProcessLayer::run(), CpuConcatenateWidthKernel::run_op(), CpuConcatenateHeightKernel::run_op(), and arm_compute::test::validation::reference::scale().
|
inline |
Dequantize a value given a 16-bit symmetric quantization scheme.
| [in] | value | Value to dequantize |
| [in] | qinfo | Quantization information to use for dequantizing |
Definition at line 508 of file QuantizationInfo.h.
References dequantize_qsymm16(), arm_compute::test::validation::qinfo, and QuantizationInfo::uniform().
|
inline |
Dequantize a value given a 16-bit symmetric quantization scheme.
| [in] | value | Value to dequantize |
| [in] | qinfo | Quantization information to use for dequantizing |
Definition at line 484 of file QuantizationInfo.h.
References arm_compute::test::validation::qinfo, and QuantizationInfo::scale().
Referenced by arm_compute::cpu::compute_all_anchors_qasymm16(), arm_compute::test::validation::convert_from_symmetric(), dequantize_qsymm16(), and arm_compute::cpu::neon_qsymm16_activation().
|
inline |
Dequantize a value given a 8-bit symmetric quantization scheme.
| [in] | value | Value to dequantize |
| [in] | qinfo | Quantization information to use for dequantizing |
Definition at line 405 of file QuantizationInfo.h.
References arm_compute::test::validation::qinfo, and QuantizationInfo::scale().
|
inline |
Dequantize a value given a 32-bit asymmetric quantization scheme.
| [in] | value | Value to dequantize |
| [in] | qinfo | Quantization information to use for dequantizing |
Definition at line 586 of file QuantizationInfo.h.
References dequantize_s32(), arm_compute::test::validation::qinfo, and QuantizationInfo::uniform().
|
inline |
Dequantize a value given a 32-bit asymmetric quantization scheme.
| [in] | value | Value to dequantize |
| [in] | qinfo | Quantization information to use for dequantizing |
Definition at line 573 of file QuantizationInfo.h.
References QuantizationInfo::offset(), arm_compute::test::validation::qinfo, and QuantizationInfo::scale().
Referenced by dequantize_s32(), and arm_compute::test::validation::reference::quantization_layer().
| bool device_supports_extension | ( | const cl::Device & | device, |
| const char * | extension_name | ||
| ) |
Helper function to check whether a given extension is supported.
| [in] | device | A CL device |
| [in] | extension_name | Name of the extension to be checked |
Definition at line 285 of file CLHelpers.cpp.
References check_header_guards::extensions.
Referenced by arm_matrix_multiply_supported(), arm_non_uniform_workgroup_supported(), command_buffer_mutable_dispatch_supported(), command_buffer_supported(), dot8_acc_supported(), dot8_supported(), fp16_supported(), image2d_from_buffer_supported(), and arm_compute::test::validation::TEST_CASE().
|
constexpr |
Calculate the rounded up quotient of val / m.
| [in] | val | Value to divide and round up. |
| [in] | m | Value to divide by. |
Definition at line 37 of file Math.h.
Referenced by ceil_to_multiple(), and arm_compute::misc::shape_calculator::compute_indirect_buffer_shape().
| bool dot8_acc_supported | ( | const cl::Device & | device | ) |
Helper function to check whether the cl_arm_integer_dot_product_accumulate_int8 extension is supported.
| [in] | device | A CL device |
Definition at line 253 of file CLHelpers.cpp.
References device_supports_extension().
| bool dot8_supported | ( | const cl::Device & | device | ) |
Helper function to check whether the cl_arm_integer_dot_product_int8 extension is supported.
| [in] | device | A CL device |
Definition at line 242 of file CLHelpers.cpp.
References device_supports_extension(), G76, and get_target_from_name().
Referenced by ClGemmLowpMatrixMultiplyNativeKernel::configure(), ClGemmLowpMatrixMultiplyReshapedKernel::configure(), ClGemmLowpMatrixMultiplyReshapedOnlyRhsKernel::configure(), and ClGemmLowpMatrixAReductionKernel::configure().
|
inline |
The size in bytes of the data type.
| [in] | dt | Input data type |
Definition at line 78 of file DataTypeUtils.h.
References ARM_COMPUTE_ERROR, BFLOAT16, dt, F16, F32, QASYMM16, QASYMM8, QASYMM8_SIGNED, QSYMM16, QSYMM8, QSYMM8_PER_CHANNEL, S16, S32, S64, S8, U16, U32, U64, and U8.
Referenced by CLPadLayerKernel::configure(), arm_compute::test::validation::reference::depth_convert(), SimpleTensor< uint8_t >::element_size(), and arm_compute::test::validation::validate().
| void enqueue | ( | cl::CommandQueue & | queue, |
| ICLKernel & | kernel, | ||
| const Window & | window, | ||
| const cl::NDRange & | lws_hint = CLKernelLibrary::get().default_ndrange(), |
||
| bool | use_dummy_work_items = false |
||
| ) |
Add the kernel to the command queue with the given window.
| [in,out] | queue | OpenCL command queue. |
| [in] | kernel | Kernel to enqueue |
| [in] | window | Window the kernel has to process. |
| [in] | lws_hint | (Optional) Local workgroup size requested. Default is based on the device target. |
| [in] | use_dummy_work_items | (Optional) Use dummy work items in order to have two dimensional power of two NDRange. Default is false Note: it is kernel responsibility to check if the work-item is out-of-range |
Definition at line 33 of file ICLKernel.cpp.
References ARM_COMPUTE_ERROR_ON, ICLKernel::cache_gws(), arm_compute::mlgo::parser::end(), ICLKernel::get_max_workgroup_size(), ICLKernel::kernel(), set_wbsm(), arm_compute::cpu::step, and ICLKernel::wbsm_hint().
Referenced by ICLSimple2DKernel::run(), ICLSimple3DKernel::run(), CLBitwiseKernel::run(), CLChannelShuffleLayerKernel::run(), CLSpaceToDepthLayerKernel::run(), CLDepthToSpaceLayerKernel::run(), CLDeconvolutionLayerUpsampleKernel::run(), CLInstanceNormalizationLayerKernel::run(), CLFFTScaleKernel::run(), CLSelectKernel::run(), CLComputeAllAnchorsKernel::run(), CLNormalizationLayerKernel::run(), CLRangeKernel::run(), CLReorgLayerKernel::run(), CLTileKernel::run(), CLQLSTMLayerNormalizationKernel::run(), CLROIPoolingLayerKernel::run(), CLMaxUnpoolingLayerKernel::run(), CLMeanStdDevNormalizationKernel::run(), CLGatherKernel::run(), CLComparisonKernel::run(), CLFFTDigitReverseKernel::run(), CLReverseKernel::run(), CLNormalizePlanarYUVLayerKernel::run(), CLReductionOperationKernel::run(), CLFFTRadixStageKernel::run(), CLArgMinMaxLayerKernel::run(), CLL2NormalizeLayerKernel::run(), CLPadLayerKernel::run(), CLFillBorderKernel::run(), CLBoundingBoxTransformKernel::run(), CLPriorBoxLayerKernel::run(), CLStackLayerKernel::run(), CLROIAlignLayerKernel::run(), CLDeconvolutionReshapeOutputKernel::run(), CLDepthwiseConvolutionLayerNativeKernel::run(), CLBatchNormalizationLayerKernel::run(), CLComputeMeanVariance::run(), CLBatchToSpaceLayerKernel::run(), CLFuseBatchNormalizationKernel::run(), CLSpaceToBatchLayerKernel::run(), ClElementwiseKernel::run_op(), ClKernelRuntime::run_op(), ClReshapeKernel::run_op(), ClTransposeKernel::run_op(), ClDequantizeKernel::run_op(), ClFloorKernel::run_op(), ClWidthConcatenate2TensorsKernel::run_op(), ClCopyKernel::run_op(), ClElementWiseUnaryKernel::run_op(), ClFillKernel::run_op(), ClHeightConcatenateKernel::run_op(), ClQuantizeKernel::run_op(), ClWidthConcatenateKernel::run_op(), ClScaleKernel::run_op(), ClPool3dKernel::run_op(), ClTransposedConvolutionKernel::run_op(), ClBatchConcatenateKernel::run_op(), ClDepthConcatenateKernel::run_op(), ClActivationKernel::run_op(), ClPermuteKernel::run_op(), ClPool2dKernel::run_op(), ClSoftmaxKernel::run_op(), ClMatMulLowpNativeMMULKernel::run_op(), ClWidthConcatenate4TensorsKernel::run_op(), ClConvertFullyConnectedWeightsKernel::run_op(), ClWinogradFilterTransformKernel::run_op(), ClWinogradInputTransformKernel::run_op(), ClMatMulNativeKernel::run_op(), ClGemmReshapeLhsMatrixKernel::run_op(), ClCastKernel::run_op(), ClMatMulLowpNativeKernel::run_op(), ClCropKernel::run_op(), ClGemmLowpQuantizeDownInt32ScaleByFixedPointKernel::run_op(), ClGemmLowpMatrixMultiplyNativeKernel::run_op(), ClGemmLowpQuantizeDownInt32ScaleByFloatKernel::run_op(), ClIndirectConv2dAddressPrecalculationKernel::run_op(), ClGemmLowpQuantizeDownInt32ScaleKernel::run_op(), ClGemmReshapeRhsMatrixKernel::run_op(), ClWinogradOutputTransformKernel::run_op(), ClCol2ImKernel::run_op(), ClGemmMatrixMultiplyNativeKernel::run_op(), ClGemmLowpMatrixMultiplyReshapedKernel::run_op(), ClIndirectConv2dKernel::run_op(), ClGemmMatrixMultiplyReshapedOnlyRhsMMULKernel::run_op(), CLStridedSliceKernel::run_op(), ClGemmLowpOffsetContributionKernel::run_op(), ClDirectConv3dKernel::run_op(), ClWeightsReshapeKernel::run_op(), ClMatMulNativeMMULKernel::run_op(), ClGemmLowpMatrixAReductionKernel::run_op(), ClDirectConv2dKernel::run_op(), ClGemmLowpOffsetContributionOutputStageKernel::run_op(), ClMulKernel::run_op(), CLFillBorderKernel::run_op(), ClGemmLowpMatrixMultiplyReshapedOnlyRhsKernel::run_op(), ClIm2ColKernel::run_op(), ClGemmMatrixMultiplyReshapedOnlyRhsKernel::run_op(), ClGemmMatrixMultiplyReshapedKernel::run_op(), ClGemmLowpMatrixBReductionKernel::run_op(), and ClComplexMulKernel::run_op().
|
inline |
Return an error if the channel is not in channels.
| [in] | function | Function in which the error occurred. |
| [in] | file | Name of the file where the error occurred. |
| [in] | line | Line on which the error occurred. |
| [in] | cn | Input channel |
| [in] | channel | First channel allowed. |
| [in] | channels | (Optional) Further allowed channels. |
Definition at line 1036 of file Validate.h.
References ARM_COMPUTE_RETURN_ERROR_ON_LOC, and UNKNOWN.
Referenced by error_on_channel_not_in_known_format().
| arm_compute::Status error_on_channel_not_in_known_format | ( | const char * | function, |
| const char * | file, | ||
| const int | line, | ||
| arm_compute::Format | fmt, | ||
| arm_compute::Channel | cn | ||
| ) |
Return an error if the channel is not in format.
| [in] | function | Function in which the error occurred. |
| [in] | file | Name of the file where the error occurred. |
| [in] | line | Line on which the error occurred. |
| [in] | fmt | Input channel |
| [in] | cn | First channel allowed. |
Definition at line 127 of file Validate.cpp.
References A, ARM_COMPUTE_ERROR_LOC, ARM_COMPUTE_RETURN_ERROR_ON_LOC, B, error_on_channel_not_in(), G, IYUV, NV12, NV21, R, RGB888, RGBA8888, U, UNKNOWN, UV88, UYVY422, V, Y, YUV444, and YUYV422.
| arm_compute::Status error_on_coordinates_dimensions_gte | ( | const char * | function, |
| const char * | file, | ||
| const int | line, | ||
| const Coordinates & | pos, | ||
| unsigned int | max_dim | ||
| ) |
Return an error if the passed coordinates have too many dimensions.
The coordinates have too many dimensions if any of the dimensions greater or equal to max_dim is different from 0.
| [in] | function | Function in which the error occurred. |
| [in] | file | Name of the file where the error occurred. |
| [in] | line | Line on which the error occurred. |
| [in] | pos | Coordinates to validate |
| [in] | max_dim | Maximum number of dimensions allowed. |
Definition at line 80 of file Validate.cpp.
References ARM_COMPUTE_RETURN_ERROR_ON_LOC, and Dimensions< int >::num_max_dimensions.
|
inline |
Return an error if the data layout of the passed tensor does not match any of the data layout provided.
| [in] | function | Function in which the error occurred. |
| [in] | file | Name of the file where the error occurred. |
| [in] | line | Line on which the error occurred. |
| [in] | tensor | Tensor to validate. |
| [in] | dl | First data layout allowed. |
| [in] | dls | (Optional) Further allowed data layouts. |
Definition at line 880 of file Validate.h.
References ARM_COMPUTE_RETURN_ERROR_ON_LOC, ARM_COMPUTE_RETURN_ON_ERROR, dl, error_on_data_layout_not_in(), CLTensor::info(), and tensor.
|
inline |
Return an error if the data layout of the passed tensor info does not match any of the data layouts provided.
| [in] | function | Function in which the error occurred. |
| [in] | file | Name of the file where the error occurred. |
| [in] | line | Line on which the error occurred. |
| [in] | tensor_info | Tensor info to validate. |
| [in] | dl | First data layout allowed. |
| [in] | dls | (Optional) Further allowed data layouts. |
Definition at line 853 of file Validate.h.
References ARM_COMPUTE_RETURN_ERROR_ON_LOC, ARM_COMPUTE_RETURN_ERROR_ON_LOC_MSG_VAR, TensorInfo::data_layout(), dl, string_from_data_layout(), tensor_info, and UNKNOWN.
Referenced by error_on_data_layout_not_in().
|
inline |
Return an error if the data type or the number of channels of the passed tensor does not match any of the data types and number of channels provided.
| [in] | function | Function in which the error occurred. |
| [in] | file | Name of the file where the error occurred. |
| [in] | line | Line on which the error occurred. |
| [in] | tensor | Tensor to validate. |
| [in] | num_channels | Number of channels to check |
| [in] | dt | First data type allowed. |
| [in] | dts | (Optional) Further allowed data types. |
Definition at line 936 of file Validate.h.
References ARM_COMPUTE_RETURN_ERROR_ON_LOC, ARM_COMPUTE_RETURN_ON_ERROR, dt, error_on_data_type_channel_not_in(), CLTensor::info(), and tensor.
|
inline |
Return an error if the data type or the number of channels of the passed tensor info does not match any of the data types and number of channels provided.
| [in] | function | Function in which the error occurred. |
| [in] | file | Name of the file where the error occurred. |
| [in] | line | Line on which the error occurred. |
| [in] | tensor_info | Tensor info to validate. |
| [in] | num_channels | Number of channels to check |
| [in] | dt | First data type allowed. |
| [in] | dts | (Optional) Further allowed data types. |
Definition at line 907 of file Validate.h.
References ARM_COMPUTE_RETURN_ERROR_ON_LOC_MSG_VAR, ARM_COMPUTE_RETURN_ON_ERROR, dt, error_on_data_type_not_in(), TensorInfo::num_channels(), and tensor_info.
Referenced by error_on_data_type_channel_not_in().
|
inline |
Return an error if the data type of the passed tensor does not match any of the data types provided.
| [in] | function | Function in which the error occurred. |
| [in] | file | Name of the file where the error occurred. |
| [in] | line | Line on which the error occurred. |
| [in] | tensor | Tensor to validate. |
| [in] | dt | First data type allowed. |
| [in] | dts | (Optional) Further allowed data types. |
Definition at line 828 of file Validate.h.
References ARM_COMPUTE_RETURN_ERROR_ON_LOC, ARM_COMPUTE_RETURN_ON_ERROR, dt, error_on_data_type_not_in(), CLTensor::info(), and tensor.
|
inline |
Return an error if the data type of the passed tensor info does not match any of the data types provided.
| [in] | function | Function in which the error occurred. |
| [in] | file | Name of the file where the error occurred. |
| [in] | line | Line on which the error occurred. |
| [in] | tensor_info | Tensor info to validate. |
| [in] | dt | First data type allowed. |
| [in] | dts | (Optional) Further allowed data types. |
Definition at line 801 of file Validate.h.
References ARM_COMPUTE_RETURN_ERROR_ON_LOC, ARM_COMPUTE_RETURN_ERROR_ON_LOC_MSG_VAR, TensorInfo::data_type(), dt, string_from_data_type(), tensor_info, and UNKNOWN.
Referenced by error_on_data_type_channel_not_in(), and error_on_data_type_not_in().
| void arm_compute::error_on_format_not_in | ( | const char * | function, |
| const char * | file, | ||
| const int | line, | ||
| const T * | object, | ||
| F && | format, | ||
| Fs &&... | formats | ||
| ) |
Throw an error if the format of the passed tensor/multi-image does not match any of the formats provided.
| [in] | function | Function in which the error occurred. |
| [in] | file | Name of the file where the error occurred. |
| [in] | line | Line on which the error occurred. |
| [in] | object | Tensor/multi-image to validate. |
| [in] | format | First format allowed. |
| [in] | formats | (Optional) Further allowed formats. |
Definition at line 767 of file Validate.h.
References ARM_COMPUTE_ERROR_ON_LOC, ARM_COMPUTE_ERROR_ON_LOC_MSG, ARM_COMPUTE_UNUSED, update_supported_ops::format, string_from_format(), and UNKNOWN.
| arm_compute::Status error_on_invalid_subtensor | ( | const char * | function, |
| const char * | file, | ||
| const int | line, | ||
| const TensorShape & | parent_shape, | ||
| const Coordinates & | coords, | ||
| const TensorShape & | shape | ||
| ) |
Return an error if if the coordinates and shape of the subtensor are within the parent tensor.
| [in] | function | Function in which the error occurred. |
| [in] | file | Name of the file where the error occurred. |
| [in] | line | Line on which the error occurred. |
| [in] | parent_shape | Parent tensor shape |
| [in] | coords | Coordinates inside the parent tensor where the first element of the subtensor is |
| [in] | shape | Shape of the subtensor |
Definition at line 174 of file Validate.cpp.
References ARM_COMPUTE_RETURN_ERROR_ON_LOC, and arm_compute::test::validation::shape.
| arm_compute::Status error_on_invalid_subtensor_valid_region | ( | const char * | function, |
| const char * | file, | ||
| const int | line, | ||
| const ValidRegion & | parent_valid_region, | ||
| const ValidRegion & | valid_region | ||
| ) |
Return an error if the valid region of a subtensor is not inside the valid region of the parent tensor.
| [in] | function | Function in which the error occurred. |
| [in] | file | Name of the file where the error occurred. |
| [in] | line | Line on which the error occurred. |
| [in] | parent_valid_region | Parent valid region. |
| [in] | valid_region | Valid region of subtensor. |
Definition at line 191 of file Validate.cpp.
References ValidRegion::anchor, ARM_COMPUTE_RETURN_ERROR_ON_LOC, ValidRegion::shape, and arm_compute::test::validation::valid_region.
| arm_compute::Status error_on_invalid_subwindow | ( | const char * | function, |
| const char * | file, | ||
| const int | line, | ||
| const Window & | full, | ||
| const Window & | sub | ||
| ) |
Return an error if the passed subwindow is invalid.
The subwindow is invalid if:
| [in] | function | Function in which the error occurred. |
| [in] | file | Name of the file where the error occurred. |
| [in] | line | Line on which the error occurred. |
| [in] | full | Full size window |
| [in] | sub | Sub-window to validate. |
Definition at line 44 of file Validate.cpp.
References ARM_COMPUTE_RETURN_ERROR_ON_LOC, arm_compute::mlgo::parser::end(), Dimensions< int >::num_max_dimensions, arm_compute::cpu::step, and Window::validate().
|
inline |
Return an error if the passed tensors have different data layouts.
| [in] | function | Function in which the error occurred. |
| [in] | file | Name of the file where the error occurred. |
| [in] | line | Line on which the error occurred. |
| [in] | tensor | The first tensor to be compared. |
| [in] | tensors | (Optional) Further allowed tensors. |
Definition at line 613 of file Validate.h.
References ARM_COMPUTE_RETURN_ERROR_ON_LOC, ARM_COMPUTE_RETURN_ON_ERROR, error_on_mismatching_data_layouts(), error_on_nullptr(), CLTensor::info(), and tensor.
|
inline |
Return an error if the passed tensor infos have different data layouts.
| [in] | function | Function in which the error occurred. |
| [in] | file | Name of the file where the error occurred. |
| [in] | line | Line on which the error occurred. |
| [in] | tensor_info | The first tensor info to be compared. |
| [in] | tensor_infos | (Optional) Further allowed tensor infos. |
Definition at line 588 of file Validate.h.
References ARM_COMPUTE_RETURN_ERROR_ON_LOC, ARM_COMPUTE_RETURN_ERROR_ON_LOC_MSG, ARM_COMPUTE_RETURN_ON_ERROR, TensorInfo::data_layout(), error_on_nullptr(), and tensor_info.
Referenced by error_on_mismatching_data_layouts().
|
inline |
Return an error if the passed two tensors have different data types.
| [in] | function | Function in which the error occurred. |
| [in] | file | Name of the file where the error occurred. |
| [in] | line | Line on which the error occurred. |
| [in] | tensor | The first tensor to be compared. |
| [in] | tensors | (Optional) Further allowed tensors. |
Definition at line 665 of file Validate.h.
References ARM_COMPUTE_RETURN_ERROR_ON_LOC, ARM_COMPUTE_RETURN_ON_ERROR, error_on_mismatching_data_types(), error_on_nullptr(), CLTensor::info(), and tensor.
|
inline |
Return an error if the passed two tensor infos have different data types.
| [in] | function | Function in which the error occurred. |
| [in] | file | Name of the file where the error occurred. |
| [in] | line | Line on which the error occurred. |
| [in] | tensor_info | The first tensor info to be compared. |
| [in] | tensor_infos | (Optional) Further allowed tensor infos. |
Definition at line 640 of file Validate.h.
References ARM_COMPUTE_RETURN_ERROR_ON_LOC, ARM_COMPUTE_RETURN_ERROR_ON_LOC_MSG, ARM_COMPUTE_RETURN_ON_ERROR, TensorInfo::data_type(), error_on_nullptr(), and tensor_info.
Referenced by error_on_mismatching_data_types().
| arm_compute::Status arm_compute::error_on_mismatching_dimensions | ( | const char * | function, |
| const char * | file, | ||
| int | line, | ||
| const Dimensions< T > & | dim1, | ||
| const Dimensions< T > & | dim2, | ||
| Ts &&... | dims | ||
| ) |
Return an error if the passed dimension objects differ.
| [in] | function | Function in which the error occurred. |
| [in] | file | Name of the file where the error occurred. |
| [in] | line | Line on which the error occurred. |
| [in] | dim1 | The first object to be compared. |
| [in] | dim2 | The second object to be compared. |
| [in] | dims | (Optional) Further allowed objects. |
Definition at line 280 of file Validate.h.
References ARM_COMPUTE_RETURN_ON_ERROR, and arm_compute::detail::for_each_error().
|
inline |
Return an error if the passed tensor have different asymmetric quantized data types or different quantization info.
| [in] | function | Function in which the error occurred. |
| [in] | file | Name of the file where the error occurred. |
| [in] | line | Line on which the error occurred. |
| [in] | tensor_1 | The first tensor to be compared. |
| [in] | tensor_2 | The second tensor to be compared. |
| [in] | tensors | (Optional) Further allowed tensors. |
Definition at line 738 of file Validate.h.
References ARM_COMPUTE_RETURN_ON_ERROR, error_on_mismatching_quantization_info(), and ITensor::info().
|
inline |
Return an error if the passed tensor infos have different asymmetric quantized data types or different quantization info.
| [in] | function | Function in which the error occurred. |
| [in] | file | Name of the file where the error occurred. |
| [in] | line | Line on which the error occurred. |
| [in] | tensor_info_1 | The first tensor info to be compared. |
| [in] | tensor_info_2 | The second tensor info to be compared. |
| [in] | tensor_infos | (Optional) Further allowed tensor infos. |
Definition at line 695 of file Validate.h.
References ARM_COMPUTE_RETURN_ERROR_ON_LOC_MSG, ITensorInfo::data_type(), is_data_type_quantized(), ITensorInfo::quantization_info(), and tensor_info.
Referenced by error_on_mismatching_quantization_info().
|
inline |
Return an error if the passed two tensors have different shapes from the given dimension.
| [in] | function | Function in which the error occurred. |
| [in] | file | Name of the file where the error occurred. |
| [in] | line | Line on which the error occurred. |
| [in] | tensor_1 | The first tensor to be compared. |
| [in] | tensor_2 | The second tensor to be compared. |
| [in] | tensors | (Optional) Further allowed tensors. |
Definition at line 497 of file Validate.h.
References error_on_mismatching_shapes(), and arm_compute::utils::cast::U.
|
inline |
Return an error if the passed two tensor infos have different shapes from the given dimension.
| [in] | function | Function in which the error occurred. |
| [in] | file | Name of the file where the error occurred. |
| [in] | line | Line on which the error occurred. |
| [in] | tensor_info_1 | The first tensor info to be compared. |
| [in] | tensor_info_2 | The second tensor info to be compared. |
| [in] | tensor_infos | (Optional) Further allowed tensor infos. |
Definition at line 475 of file Validate.h.
References arm_compute::utils::cast::U.
Referenced by error_on_mismatching_shapes().
|
inline |
Return an error if the passed two tensors have different shapes from the given dimension.
| [in] | function | Function in which the error occurred. |
| [in] | file | Name of the file where the error occurred. |
| [in] | line | Line on which the error occurred. |
| [in] | upper_dim | The dimension from which to check. |
| [in] | tensor_1 | The first tensor to be compared. |
| [in] | tensor_2 | The second tensor to be compared. |
| [in] | tensors | (Optional) Further allowed tensors. |
Definition at line 556 of file Validate.h.
References ARM_COMPUTE_RETURN_ERROR_ON_LOC, ARM_COMPUTE_RETURN_ON_ERROR, error_on_mismatching_shapes(), error_on_nullptr(), and ITensor::info().
|
inline |
Return an error if the passed two tensors have different shapes from the given dimension.
| [in] | function | Function in which the error occurred. |
| [in] | file | Name of the file where the error occurred. |
| [in] | line | Line on which the error occurred. |
| [in] | upper_dim | The dimension from which to check. |
| [in] | tensor_info_1 | The first tensor info to be compared. |
| [in] | tensor_info_2 | The second tensor info to be compared. |
| [in] | tensor_infos | (Optional) Further allowed tensor infos. |
Definition at line 519 of file Validate.h.
References ARM_COMPUTE_RETURN_ERROR_ON_LOC, ARM_COMPUTE_RETURN_ERROR_ON_LOC_MSG, ARM_COMPUTE_RETURN_ON_ERROR, error_on_nullptr(), and tensor_info.
| arm_compute::Status error_on_mismatching_windows | ( | const char * | function, |
| const char * | file, | ||
| const int | line, | ||
| const Window & | full, | ||
| const Window & | win | ||
| ) |
Return an error if the passed window is invalid.
The subwindow is invalid if:
| [in] | function | Function in which the error occurred. |
| [in] | file | Name of the file where the error occurred. |
| [in] | line | Line on which the error occurred. |
| [in] | full | Full size window |
| [in] | win | Window to validate. |
Definition at line 26 of file Validate.cpp.
References ARM_COMPUTE_RETURN_ERROR_ON_LOC, arm_compute::mlgo::parser::end(), Dimensions< int >::num_max_dimensions, arm_compute::cpu::step, and Window::validate().
|
inline |
Create an error if one of the pointers is a nullptr.
| [in] | function | Function in which the error occurred. |
| [in] | file | Name of the file where the error occurred. |
| [in] | line | Line on which the error occurred. |
| [in] | pointers | Pointers to check against nullptr. |
Definition at line 151 of file Validate.h.
References ARM_COMPUTE_RETURN_ERROR_ON_LOC_MSG.
Referenced by error_on_mismatching_data_layouts(), error_on_mismatching_data_types(), error_on_mismatching_shapes(), error_on_tensors_not_even(), and error_on_tensors_not_subsampled().
| arm_compute::Status error_on_tensor_not_2d | ( | const char * | function, |
| const char * | file, | ||
| const int | line, | ||
| const ITensor * | tensor | ||
| ) |
Return an error if the tensor is not 2D.
| [in] | function | Function in which the error occurred. |
| [in] | file | Name of the file where the error occurred. |
| [in] | line | Line on which the error occurred. |
| [in] | tensor | Tensor to validate. |
Definition at line 102 of file Validate.cpp.
References ARM_COMPUTE_RETURN_ERROR_ON_LOC, ARM_COMPUTE_RETURN_ERROR_ON_LOC_MSG_VAR, and tensor.
| arm_compute::Status error_on_tensor_not_2d | ( | const char * | function, |
| const char * | file, | ||
| const int | line, | ||
| const ITensorInfo * | tensor | ||
| ) |
Return an error if the tensor info is not 2D.
| [in] | function | Function in which the error occurred. |
| [in] | file | Name of the file where the error occurred. |
| [in] | line | Line on which the error occurred. |
| [in] | tensor | Tensor info to validate. |
Definition at line 115 of file Validate.cpp.
References ARM_COMPUTE_RETURN_ERROR_ON_LOC, ARM_COMPUTE_RETURN_ERROR_ON_LOC_MSG_VAR, and tensor.
| arm_compute::Status arm_compute::error_on_tensors_not_even | ( | const char * | function, |
| const char * | file, | ||
| int | line, | ||
| const Format & | format, | ||
| const ITensor * | tensor1, | ||
| Ts... | tensors | ||
| ) |
Return an error if the passed tensor objects are not even.
| [in] | function | Function in which the error occurred. |
| [in] | file | Name of the file where the error occurred. |
| [in] | line | Line on which the error occurred. |
| [in] | format | Format to check if odd shape is allowed |
| [in] | tensor1 | The first object to be compared for odd shape. |
| [in] | tensors | (Optional) Further allowed objects. |
Definition at line 369 of file Validate.h.
References ARM_COMPUTE_RETURN_ERROR_ON_LOC, ARM_COMPUTE_RETURN_ERROR_ON_LOC_MSG, ARM_COMPUTE_RETURN_ON_ERROR, error_on_nullptr(), and tensor.
| arm_compute::Status arm_compute::error_on_tensors_not_subsampled | ( | const char * | function, |
| const char * | file, | ||
| int | line, | ||
| const Format & | format, | ||
| const TensorShape & | shape, | ||
| const ITensor * | tensor1, | ||
| Ts... | tensors | ||
| ) |
Return an error if the passed tensor objects are not sub-sampled.
| [in] | function | Function in which the error occurred. |
| [in] | file | Name of the file where the error occurred. |
| [in] | line | Line on which the error occurred. |
| [in] | format | Format to check if sub-sampling allowed. |
| [in] | shape | The tensor shape to calculate sub-sampling from. |
| [in] | tensor1 | The first object to be compared. |
| [in] | tensors | (Optional) Further allowed objects. |
Definition at line 436 of file Validate.h.
References ARM_COMPUTE_RETURN_ERROR_ON_LOC, ARM_COMPUTE_RETURN_ERROR_ON_LOC_MSG, ARM_COMPUTE_RETURN_ON_ERROR, calculate_subsampled_shape(), error_on_nullptr(), update_supported_ops::format, arm_compute::test::validation::shape, and tensor.
| arm_compute::Status error_on_unconfigured_kernel | ( | const char * | function, |
| const char * | file, | ||
| const int | line, | ||
| const IKernel * | kernel | ||
| ) |
Return an error if the kernel is not configured.
| [in] | function | Function in which the error occurred. |
| [in] | file | Name of the file where the error occurred. |
| [in] | line | Line on which the error occurred. |
| [in] | kernel | Kernel to validate. |
Definition at line 163 of file Validate.cpp.
References ARM_COMPUTE_RETURN_ERROR_ON_LOC, ARM_COMPUTE_RETURN_ERROR_ON_LOC_MSG, and IKernel::is_window_configured().
|
inline |
Return an error if the data type of the passed tensor is BFLOAT16 and BFLOAT16 support is not compiled in.
| [in] | function | Function in which the error occurred. |
| [in] | file | Name of the file where the error occurred. |
| [in] | line | Line on which the error occurred. |
| [in] | tensor | Tensor to validate. |
Definition at line 107 of file Validate.h.
References ARM_COMPUTE_RETURN_ERROR_ON_LOC, ARM_COMPUTE_RETURN_ON_ERROR, error_on_unsupported_cpu_bf16(), CLTensor::info(), and tensor.
|
inline |
Return an error if the data type of the passed tensor info is BFLOAT16 and BFLOAT16 support is not compiled in.
| [in] | function | Function in which the error occurred. |
| [in] | file | Name of the file where the error occurred. |
| [in] | line | Line on which the error occurred. |
| [in] | tensor_info | Tensor info to validate. |
Definition at line 66 of file Validate.h.
References ARM_COMPUTE_RETURN_ERROR_ON_LOC, ARM_COMPUTE_RETURN_ERROR_ON_LOC_MSG, BFLOAT16, TensorInfo::data_type(), CPUInfo::get(), CPUInfo::has_bf16(), and tensor_info.
Referenced by error_on_unsupported_cpu_bf16().
|
inline |
Return an error if the data type of the passed tensor is FP16 and FP16 support is not compiled in.
| [in] | function | Function in which the error occurred. |
| [in] | file | Name of the file where the error occurred. |
| [in] | line | Line on which the error occurred. |
| [in] | tensor | Tensor to validate. |
Definition at line 90 of file Validate.h.
References ARM_COMPUTE_RETURN_ERROR_ON_LOC, ARM_COMPUTE_RETURN_ON_ERROR, error_on_unsupported_cpu_fp16(), CLTensor::info(), and tensor.
|
inline |
Return an error if the data type of the passed tensor info is FP16 and FP16 support is not compiled in.
| [in] | function | Function in which the error occurred. |
| [in] | file | Name of the file where the error occurred. |
| [in] | line | Line on which the error occurred. |
| [in] | tensor_info | Tensor info to validate. |
Definition at line 42 of file Validate.h.
References ARM_COMPUTE_RETURN_ERROR_ON_LOC, ARM_COMPUTE_RETURN_ERROR_ON_LOC_MSG, TensorInfo::data_type(), F16, CPUInfo::get(), CPUInfo::has_fp16(), and tensor_info.
Referenced by error_on_unsupported_cpu_fp16().
|
inline |
Return an error if the data type of the passed tensor is FP16 and FP16 extension is not supported by the device.
| [in] | function | Function in which the error occurred. |
| [in] | file | Name of the file where the error occurred. |
| [in] | line | Line on which the error occurred. |
| [in] | tensor | Tensor to validate. |
| [in] | is_fp16_supported | Is fp16 supported by the device. |
Definition at line 985 of file Validate.h.
References ARM_COMPUTE_RETURN_ERROR_ON_LOC, ARM_COMPUTE_RETURN_ON_ERROR, error_on_unsupported_fp16(), CLTensor::info(), and tensor.
|
inline |
Return an error if the data type of the passed tensor info is FP16 and FP16 extension is not supported by the device.
| [in] | function | Function in which the error occurred. |
| [in] | file | Name of the file where the error occurred. |
| [in] | line | Line on which the error occurred. |
| [in] | tensor_info | Tensor info to validate. |
| [in] | is_fp16_supported | Is fp16 supported by the device. |
Definition at line 966 of file Validate.h.
References ARM_COMPUTE_RETURN_ERROR_ON_LOC, ARM_COMPUTE_RETURN_ERROR_ON_LOC_MSG, TensorInfo::data_type(), F16, and tensor_info.
Referenced by error_on_unsupported_fp16().
|
inline |
Return an error if int64_base_atomics extension is not supported by the device.
| [in] | function | Function in which the error occurred. |
| [in] | file | Name of the file where the error occurred. |
| [in] | line | Line on which the error occurred. |
Definition at line 49 of file CLValidate.h.
References ARM_COMPUTE_CREATE_ERROR_LOC, CLKernelLibrary::get(), and UNSUPPORTED_EXTENSION_USE.
| arm_compute::Status error_on_window_dimensions_gte | ( | const char * | function, |
| const char * | file, | ||
| const int | line, | ||
| const Window & | win, | ||
| unsigned int | max_dim | ||
| ) |
Return an error if the passed window has too many dimensions.
The window has too many dimensions if any of the dimension greater or equal to max_dim is different from 0.
| [in] | function | Function in which the error occurred. |
| [in] | file | Name of the file where the error occurred. |
| [in] | line | Line on which the error occurred. |
| [in] | win | Window to validate |
| [in] | max_dim | Maximum number of dimensions allowed. |
Definition at line 90 of file Validate.cpp.
References ARM_COMPUTE_RETURN_ERROR_ON_LOC_MSG_VAR, arm_compute::mlgo::parser::end(), Dimensions< int >::num_max_dimensions, and arm_compute::cpu::step.
| arm_compute::Status error_on_window_not_collapsable_at_dimension | ( | const char * | function, |
| const char * | file, | ||
| const int | line, | ||
| const Window & | full, | ||
| const Window & | window, | ||
| const int | dim | ||
| ) |
Return an error if the window can't be collapsed at the given dimension.
The window cannot be collapsed if the given dimension not equal to the full window's dimension or not start from 0.
| [in] | function | Function in which the error occurred. |
| [in] | file | Name of the file where the error occurred. |
| [in] | line | Line on which the error occurred. |
| [in] | full | Full size window |
| [in] | window | Window to be collapsed. |
| [in] | dim | Dimension need to be checked. |
Definition at line 63 of file Validate.cpp.
References ARM_COMPUTE_RETURN_ERROR_ON_LOC, arm_compute::mlgo::parser::end(), and Window::validate().
|
inline |
Iterate through the passed window, automatically adjusting the iterators and calling the lambda_functino for each element.
It passes the x and y positions to the lambda_function for each iteration
| [in] | w | Window to iterate through. |
| [in] | lambda_function | The function of type void(function)( const Coordinates & id ) to call at each iteration. Where id represents the absolute coordinates of the item to process. |
| [in,out] | iterators | Tensor iterators which will be updated by this function before calling lambda_function. |
Definition at line 74 of file Helpers.inl.
References ARM_COMPUTE_ERROR_ON, Dimensions< int >::num_max_dimensions, arm_compute::cpu::step, and arm_compute::test::validation::w.
Referenced by arm_compute::cpu::add_qasymm8_signed_sve2(), arm_compute::cpu::add_qasymm8_sve2(), arm_compute::cpu::add_qsymm16_neon(), arm_compute::cpu::add_qsymm16_sve2(), arm_compute::cpu::add_same_neon(), arm_compute::cpu::add_same_sve(), arm_compute::cpu::add_sub_q8_neon_fixedpoint(), arm_compute::cpu::add_sub_qasymm8_neon(), arm_compute::cpu::add_sub_qasymm8_signed_neon(), arm_compute::cpu::avg_poolingMxNxD_q8_neon_ndhwc(), arm_compute::cpu::batch_normalization_nchw(), arm_compute::cpu::bounding_box_transform(), arm_compute::cpu::bounding_box_transform_qsymm16(), colorconvert_iyuv_to_nv12(), colorconvert_iyuv_to_rgb(), colorconvert_iyuv_to_yuv4(), colorconvert_nv12_to_iyuv(), colorconvert_nv12_to_rgb(), colorconvert_nv12_to_yuv4(), colorconvert_rgb_to_iyuv(), colorconvert_rgb_to_nv12(), colorconvert_rgb_to_rgbx(), colorconvert_rgb_to_u8(), colorconvert_rgb_to_yuv4(), colorconvert_rgbx_to_rgb(), colorconvert_yuyv_to_iyuv(), colorconvert_yuyv_to_nv12(), colorconvert_yuyv_to_rgb(), arm_compute::utils::compare_tensor(), arm_compute::cpu::compute_all_anchors(), arm_compute::cpu::compute_all_anchors_qasymm16(), arm_compute::cpu::kernels::convolve_nchw(), arm_compute::cpu::kernels::convolve_nhwc(), ITensor::copy_from(), arm_compute::cpu::depthwise_loop_generic_fp(), arm_compute::cpu::depthwise_loop_multiplier1_fp(), arm_compute::cpu::directconv3d_float_neon_ndhwc(), arm_compute::cpu::directconv3d_quantized_neon_ndhwc(), arm_compute::cpu::elementwise_arithmetic_op(), arm_compute::cpu::elementwise_arithmetic_quantized_op(), arm_compute::cpu::elementwise_comp_quantized_signed(), arm_compute::cpu::elementwise_comparison_op(), arm_compute::cpu::elementwise_comparison_quantized_op(), arm_compute::cpu::elementwise_op(), arm_compute::cpu::elementwise_op< int8_t >(), arm_compute::cpu::elementwise_op< uint8_t >(), arm_compute::cpu::elementwise_op_quantized(), arm_compute::cpu::elementwise_op_quantized_signed(), arm_compute::cpu::elementwise_sve_op(), AssetsLibrary::fill_borders_with_garbage(), IImageLoader::fill_image(), AssetsLibrary::fill_layer_data(), IImageLoader::fill_planar_tensor(), arm_compute::utils::fill_random_tensor(), NPYLoader::fill_tensor(), arm_compute::utils::fill_tensor_value(), arm_compute::utils::fill_tensor_vector(), arm_compute::cpu::fp_neon_activation_impl(), arm_compute::cpu::fused_batch_normalization_conv(), arm_compute::cpu::fused_batch_normalization_dwc_nchw(), arm_compute::cpu::fused_batch_normalization_dwc_nhwc(), arm_compute::test::validation::reference::gather(), arm_compute::cpu::instance_normalization_nchw(), arm_compute::cpu::l2_normalize_x(), arm_compute::cpu::l2_normalize_yz(), arm_compute::utils::load_trained_data(), arm_compute::cpu::matrix_addition_f32(), arm_compute::cpu::matrix_matrix_multiply_f32(), arm_compute::cpu::max_poolingMxNxD_q8_neon_ndhwc(), arm_compute::cpu::max_unpooling(), arm_compute::cpu::mean_stddev_normalization(), arm_compute::cpu::mul_F32_F32_F32(), arm_compute::cpu::neon_qasymm8_activation(), arm_compute::cpu::neon_qasymm8_meanstddevnorm(), arm_compute::cpu::neon_qasymm8_signed_activation(), arm_compute::cpu::neon_qsymm16_activation(), arm_compute::cpu::neon_range_function(), arm_compute::cpu::neon_softmax_non_x_float(), arm_compute::cpu::neon_softmax_non_x_quantized(), arm_compute::cpu::neon_softmax_x_float(), arm_compute::cpu::neon_softmax_x_quantized(), normalize_float(), arm_compute::cpu::poolingMxN_fp32_neon_nhwc(), arm_compute::cpu::poolingMxN_fp32_neon_nhwc_kernel_indices(), arm_compute::cpu::poolingMxN_q8_neon_nhwc(), CPPUpsampleKernel::run(), NEBitwiseNotKernel::run(), NEBitwiseXorKernel::run(), NEBitwiseAndKernel::run(), NEBitwiseOrKernel::run(), NETileKernel::run(), NESpaceToDepthLayerKernel::run(), NEFFTScaleKernel::run(), NEReorgLayerKernel::run(), NEFFTRadixStageKernel::run(), NEBatchToSpaceLayerKernel::run(), NESpaceToBatchLayerKernel::run(), arm_compute::cpu::kernels::run_im2col(), CpuFillKernel::run_op(), CpuConvertQuantizedSignednessKernel::run_op(), CpuCopyKernel::run_op(), CpuConcatenateHeightKernel::run_op(), CpuConcatenateWidthKernel::run_op(), CpuFloorKernel::run_op(), CpuConvertFullyConnectedWeightsKernel::run_op(), CpuGemmInterleave4x4Kernel::run_op(), CpuCol2ImKernel::run_op(), CpuCastKernel::run_op(), CpuWeightsReshapeKernel::run_op(), CpuGemmTranspose1xWKernel::run_op(), NEStridedSliceKernel::run_op(), run_reverse(), arm_compute::utils::save_to_npy(), arm_compute::utils::save_to_ppm(), arm_compute::cpu::select_op(), arm_compute::test::validation::reference::slice(), arm_compute::test::validation::reference::softmax_layer_generic(), arm_compute::test::validation::reference::strided_slice(), arm_compute::cpu::sub_qsymm16_neon(), arm_compute::cpu::sub_same_neon(), arm_compute::cpu::sve2_q8_elementwise_unary(), arm_compute::cpu::sve2_qasymm8_activation(), arm_compute::cpu::sve2_qasymm8_signed_activation(), arm_compute::cpu::sve2_qsymm16_activation(), arm_compute::cpu::sve2_softmax_logits_1d_quantized(), arm_compute::cpu::sve_fp32_activation(), arm_compute::cpu::sve_logits_1d_max(), arm_compute::cpu::sve_softmax_logits_1d_float(), arm_compute::test::validation::TEST_CASE(), and arm_compute::cpu::vector_matrix_multiply_f32().
| bool export_to_cl_image | ( | const ITensorInfo * | tensor | ) |
Definition at line 449 of file CLHelpers.cpp.
References CLKernelLibrary::get(), get_cl_image_pitch_alignment(), CLKernelLibrary::get_device(), image2d_from_buffer_supported(), is_data_type_float(), and tensor.
Referenced by arm_compute::opencl::kernels::gemm::configure_lhs_rhs_info(), arm_compute::cl_dwc::use_cl_image_for_weights(), and ClComponentDepthwiseConv2d::validate().
|
inline |
Performs final quantization step on single element.
| [in] | in_value | Input to be quantized. |
| [in] | result_fixedpoint_multiplier | Result multiplier parameter |
| [in] | result_shift | Result shift parameter |
| [in] | result_offset_after_shift_s32 | Result offset parameter |
| [in] | min_s8 | Relu lower bound |
| [in] | max_s8 | Relu upper bound |
| [in] | is_bounded_relu | Specified if a fused bounded relu should be applied |
Definition at line 366 of file NEAsymm.h.
References rounding_divide_by_pow2().
|
inline |
Performs final quantization step on single element.
| [in] | in_value | Input to be quantized. |
| [in] | result_fixedpoint_multiplier | Result multiplier parameter |
| [in] | result_shift | Result shift parameter |
| [in] | result_offset_after_shift_s32 | Result offset parameter |
| [in] | min_u8 | Relu lower bound |
| [in] | max_u8 | Relu upper bound |
| [in] | is_bounded_relu | Specified if a fused bounded relu should be applied |
Definition at line 318 of file NEAsymm.h.
References rounding_divide_by_pow2().
|
inline |
Performs final quantization step on 16 elements.
| [in] | in_s32 | Input to be quantized. |
| [in] | result_fixedpoint_multiplier | Result multiplier parameter |
| [in] | result_shift | Result shift parameter |
| [in] | result_offset_after_shift_s32 | Result offset parameter |
| [in] | min_s8 | Relu lower bound |
| [in] | max_s8 | Relu upper bound |
| [in] | is_bounded_relu | Specified if a fused bounded relu should be applied |
Definition at line 161 of file NEAsymm.h.
References rounding_divide_by_pow2().
|
inline |
Performs final quantization step on 16 elements.
| [in] | in_s32 | Input to be quantized. |
| [in] | result_fixedpoint_multiplier | Result multiplier parameter |
| [in] | result_shift | Result shift parameter |
| [in] | result_offset_after_shift_s32 | Result offset parameter |
| [in] | min_u8 | Relu lower bound |
| [in] | max_u8 | Relu upper bound |
| [in] | is_bounded_relu | Specified if a fused bounded relu should be applied |
Definition at line 84 of file NEAsymm.h.
References rounding_divide_by_pow2().
Referenced by arm_compute::cpu::directconv3d_quantized_neon_ndhwc().
|
inline |
Performs final quantization step on single signed 16-bit element.
| is_bounded_relu | Specified if a fused bounded relu should be applied |
| [in] | in_value | Input to be quantized. |
| [in] | result_fixedpoint_multiplier | Result multiplier parameter |
| [in] | result_shift | Result shift parameter |
| [in] | min_s16 | Relu lower bound |
| [in] | max_s16 | Relu upper bound |
Definition at line 100 of file NESymm.h.
References rounding_divide_by_pow2().
| int16x8_t arm_compute::finalize_quantization_int16 | ( | int32x4x2_t & | in_s32, |
| int | result_fixedpoint_multiplier, | ||
| int32_t | result_shift, | ||
| int16x8_t | min_s16, | ||
| int16x8_t | max_s16 | ||
| ) |
Performs final quantization step on 8 signed 16-bit elements.
| is_bounded_relu | Specified if a fused bounded relu should be applied |
| [in] | in_s32 | Input to be quantized. |
| [in] | result_fixedpoint_multiplier | Result multiplier parameter |
| [in] | result_shift | Result shift parameter |
| [in] | min_s16 | Relu lower bound |
| [in] | max_s16 | Relu upper bound |
Definition at line 54 of file NESymm.h.
References rounding_divide_by_pow2().
|
inline |
Performs final quantization step on 16 elements for symmetric quantization.
| [in] | in_s32 | Input to be quantized. |
| [in] | result_fixedpoint_multiplier | Result multiplier parameter |
| [in] | result_shift | Result shift parameter |
| [in] | result_offset_after_shift_s32 | Result offset parameter |
| [in] | min_s8 | Relu lower bound |
| [in] | max_s8 | Relu upper bound |
| [in] | is_bounded_relu | Specified if a fused bounded relu should be applied |
Definition at line 230 of file NEAsymm.h.
References rounding_divide_by_pow2().
| std::string float_to_string_with_full_precision | ( | float | val | ) |
Create a string with the float in full precision.
| val | Floating point value |
Definition at line 52 of file StringUtils.cpp.
References arm_compute::test::validation::ss().
Referenced by ClDequantizeKernel::configure(), ClElementWiseUnaryKernel::configure(), ClWidthConcatenate2TensorsKernel::configure(), ClPool3dKernel::configure(), ClPool2dKernel::configure(), ClQuantizeKernel::configure(), ClScaleKernel::configure(), ClWidthConcatenateKernel::configure(), ClHeightConcatenateKernel::configure(), ClWidthConcatenate4TensorsKernel::configure(), ClActivationKernel::configure(), ClMatMulNativeKernel::configure(), ClDepthConcatenateKernel::configure(), ClBatchConcatenateKernel::configure(), ClGemmMatrixMultiplyNativeKernel::configure(), CLInstanceNormalizationLayerKernel::configure(), ClGemmMatrixMultiplyReshapedOnlyRhsMMULKernel::configure(), ClIndirectConv2dKernel::configure(), ClWinogradOutputTransformKernel::configure(), ClGemmLowpQuantizeDownInt32ScaleByFloatKernel::configure(), CLComputeAllAnchorsKernel::configure(), CLNormalizationLayerKernel::configure(), ClSoftmaxKernel::configure(), CLComparisonKernel::configure(), CLMeanStdDevNormalizationKernel::configure(), CLRangeKernel::configure(), CLReductionOperationKernel::configure(), ClDirectConv2dKernel::configure(), ClMulKernel::configure(), ClGemmMatrixMultiplyReshapedOnlyRhsKernel::configure(), CLDepthwiseConvolutionLayerNativeKernel::configure(), CLBoundingBoxTransformKernel::configure(), CLROIPoolingLayerKernel::configure(), CLROIAlignLayerKernel::configure(), ClGemmMatrixMultiplyReshapedKernel::configure(), CLFuseBatchNormalizationKernel::configure(), CLBatchNormalizationLayerKernel::configure(), ClComplexMulKernel::configure(), and string_from_pixel_value().
|
inline |
Computes the largest number smaller or equal to value that is a multiple of divisor.
| [in] | value | Upper bound value |
| [in] | divisor | Value to compute multiple of. |
Definition at line 64 of file Math.h.
References ARM_COMPUTE_ERROR_ON.
| bool fp16_supported | ( | const cl::Device & | device | ) |
Helper function to check whether the cl_khr_fp16 extension is supported.
| [in] | device | A CL device |
Definition at line 237 of file CLHelpers.cpp.
References device_supports_extension().
Helper function to get the GPU arch.
| [in] | target | GPU target |
Definition at line 247 of file GPUTarget.cpp.
References GPU_ARCH_MASK.
Referenced by ClFullyConnected::configure(), ClIndirectConvKernelConfigurationFactory::create(), ClMatMulNativeKernelConfigurationFactory::create(), ClDWCNativeKernelConfigurationFactory::create(), ClDirectConvKernelConfigurationFactory::create(), CLGEMMKernelSelectionFactory::create(), ClMatMulNativeKernelVariantFactory::create(), ClGemmReshapedOnlyRhsKernelConfigurationFactory::create(), ClGemmReshapedKernelConfigurationFactory::create(), ClGemmNativeKernelConfigurationFactory::create(), GpuDepthwiseConv2d::create_op(), ClConv2d::get_convolution_method(), and ClFullyConnected::validate().
| std::string get_cl_dot8_acc_type_from_data_type | ( | const DataType & | dt | ) |
Translates a tensor data type to the appropriate OpenCL dot8 accumulator type.
| [in] | dt | DataType to be translated to OpenCL dot8 accumulator type. |
Definition at line 176 of file CLHelpers.cpp.
References ARM_COMPUTE_ERROR, dt, QASYMM8, QASYMM8_SIGNED, QSYMM8, QSYMM8_PER_CHANNEL, S8, and U8.
Referenced by ClGemmLowpMatrixMultiplyNativeKernel::configure(), ClGemmLowpMatrixMultiplyReshapedKernel::configure(), ClGemmLowpMatrixMultiplyReshapedOnlyRhsKernel::configure(), ClGemmLowpMatrixAReductionKernel::configure(), and ClGemmLowpMatrixBReductionKernel::configure().
| size_t get_cl_image_pitch_alignment | ( | const cl::Device & | device | ) |
Helper function to get the cl_image pitch alignment in pixels.
| [in] | device | A CL device |
Definition at line 382 of file CLHelpers.cpp.
References clGetDeviceInfo().
Referenced by create_image2d_from_buffer(), export_to_cl_image(), examples::gemm_tuner_helpers::update_padding_for_cl_image(), arm_compute::opencl::kernels::gemm::update_padding_for_cl_image(), and arm_compute::opencl::kernels::gemm::validate_image2d_support_on_rhs().
| bool get_cl_non_uniform_work_group_supported | ( | const cl::Device & | device | ) |
Helper function to check whether non-uniform work group is supported.
| [in] | device | A CL device |
Definition at line 398 of file CLHelpers.cpp.
References clGetDeviceInfo().
Referenced by CLDevice::is_non_uniform_workgroup_supported().
| std::string get_cl_promoted_type_from_data_type | ( | const DataType & | dt | ) |
Translates a tensor data type to the appropriate OpenCL promoted type.
| [in] | dt | DataType to be used to get the promoted OpenCL type. |
Definition at line 77 of file CLHelpers.cpp.
References ARM_COMPUTE_ERROR, dt, F16, QASYMM16, QASYMM8, QASYMM8_SIGNED, QSYMM16, QSYMM8, QSYMM8_PER_CHANNEL, S16, S32, S8, U16, U32, and U8.
| std::string get_cl_select_type_from_data_type | ( | const DataType & | dt | ) |
Translates a tensor data type to the appropriate OpenCL select type.
| [in] | dt | DataType to be translated to OpenCL select type. |
Definition at line 143 of file CLHelpers.cpp.
References ARM_COMPUTE_ERROR, dt, F16, F32, QASYMM16, QASYMM8, QASYMM8_SIGNED, QSYMM16, QSYMM8, QSYMM8_PER_CHANNEL, S16, S32, S64, S8, U16, U32, U64, and U8.
Referenced by CLArgMinMaxLayerKernel::configure().
| std::string get_cl_signed_type_from_element_size | ( | size_t | element_size | ) |
Translates the element size to an signed integer data type.
| [in] | element_size | Size in bytes of an element. |
Definition at line 125 of file CLHelpers.cpp.
References ARM_COMPUTE_ERROR.
| std::string get_cl_type_from_data_type | ( | const DataType & | dt | ) |
Translates a tensor data type to the appropriate OpenCL type.
| [in] | dt | DataType to be translated to OpenCL type. |
Definition at line 41 of file CLHelpers.cpp.
References ARM_COMPUTE_ERROR, dt, F16, F32, QASYMM16, QASYMM8, QASYMM8_SIGNED, QSYMM16, QSYMM8, QSYMM8_PER_CHANNEL, S16, S32, S64, S8, U16, U32, U64, and U8.
Referenced by ClTransposedConvolutionKernel::configure(), ClDequantizeKernel::configure(), ClFloorKernel::configure(), ClElementWiseUnaryKernel::configure(), ClCopyKernel::configure(), ClFillKernel::configure(), ClWidthConcatenate2TensorsKernel::configure(), ClMatMulLowpNativeMMULKernel::configure(), ClPool3dKernel::configure(), ClPool2dKernel::configure(), ClQuantizeKernel::configure(), ClScaleKernel::configure(), ClWidthConcatenateKernel::configure(), ClWidthConcatenate4TensorsKernel::configure(), ClActivationKernel::configure(), ClCropKernel::configure(), ClMatMulNativeKernel::configure(), ClDepthConcatenateKernel::configure(), ClBatchConcatenateKernel::configure(), ClMatMulLowpNativeKernel::configure(), ClGemmLowpMatrixMultiplyNativeKernel::configure(), ClGemmMatrixMultiplyNativeKernel::configure(), CLInstanceNormalizationLayerKernel::configure(), ClWinogradFilterTransformKernel::configure(), ClWinogradInputTransformKernel::configure(), ClGemmLowpQuantizeDownInt32ScaleByFixedPointKernel::configure(), ClGemmMatrixMultiplyReshapedOnlyRhsMMULKernel::configure(), ClIndirectConv2dAddressPrecalculationKernel::configure(), ClIndirectConv2dKernel::configure(), ClWinogradOutputTransformKernel::configure(), ClGemmLowpQuantizeDownInt32ScaleByFloatKernel::configure(), ClGemmLowpQuantizeDownInt32ScaleKernel::configure(), CLComputeAllAnchorsKernel::configure(), ClSoftmaxKernel::configure(), CLNormalizationLayerKernel::configure(), CLQLSTMLayerNormalizationKernel::configure(), CLFFTScaleKernel::configure(), CLComparisonKernel::configure(), ClGemmLowpMatrixMultiplyReshapedKernel::configure(), ClCastKernel::configure(), CLMeanStdDevNormalizationKernel::configure(), CLFFTDigitReverseKernel::configure(), ClGemmLowpOffsetContributionOutputStageKernel::configure(), CLBatchToSpaceLayerKernel::configure(), CLReorgLayerKernel::configure(), CLNormalizePlanarYUVLayerKernel::configure(), CLRangeKernel::configure(), CLReductionOperationKernel::configure(), ClDirectConv2dKernel::configure(), ClCol2ImKernel::configure(), CLFFTRadixStageKernel::configure(), ClDirectConv3dKernel::configure(), ClGemmLowpMatrixMultiplyReshapedOnlyRhsKernel::configure(), CLL2NormalizeLayerKernel::configure(), CLPadLayerKernel::configure(), ClMatMulNativeMMULKernel::configure(), ClMulKernel::configure(), CLArgMinMaxLayerKernel::configure(), CLDepthwiseConvolutionLayerNativeKernel::configure(), CLBoundingBoxTransformKernel::configure(), ClGemmMatrixMultiplyReshapedOnlyRhsKernel::configure(), CLPriorBoxLayerKernel::configure(), CLROIPoolingLayerKernel::configure(), CLStackLayerKernel::configure(), CLROIAlignLayerKernel::configure(), ClGemmLowpMatrixAReductionKernel::configure(), CLFillBorderKernel::configure(), ClGemmMatrixMultiplyReshapedKernel::configure(), CLDeconvolutionReshapeOutputKernel::configure(), CLFuseBatchNormalizationKernel::configure(), CLBatchNormalizationLayerKernel::configure(), CLComputeMeanVariance::configure(), ClComplexMulKernel::configure(), and ClGemmLowpMatrixBReductionKernel::configure().
| std::string get_cl_unsigned_type_from_element_size | ( | size_t | element_size | ) |
Translates the element size to an unsigned integer data type.
| [in] | element_size | Size in bytes of an element. |
Definition at line 107 of file CLHelpers.cpp.
References ARM_COMPUTE_ERROR.
Referenced by ClReshapeKernel::configure(), ClHeightConcatenateKernel::configure(), ClPermuteKernel::configure(), CLStridedSliceKernel::configure(), ClConvertFullyConnectedWeightsKernel::configure(), ClGemmReshapeLhsMatrixKernel::configure(), CLMaxUnpoolingLayerKernel::configure(), CLChannelShuffleLayerKernel::configure(), CLSelectKernel::configure(), CLDeconvolutionLayerUpsampleKernel::configure(), CLDepthToSpaceLayerKernel::configure(), CLSpaceToDepthLayerKernel::configure(), CLSpaceToBatchLayerKernel::configure(), CLGatherKernel::configure(), CLTileKernel::configure(), ClGemmReshapeRhsMatrixKernel::configure(), CLReverseKernel::configure(), ClWeightsReshapeKernel::configure(), and CLBatchToSpaceLayerKernel::configure().
| CLVersion get_cl_version | ( | const cl::Device & | device | ) |
Helper function to get the highest OpenCL version supported.
| [in] | device | A CL device |
Definition at line 258 of file CLHelpers.cpp.
References CL10, CL11, CL12, CL20, CL30, and UNKNOWN.
Referenced by CLDevice::CLDevice().
|
inline |
Get the index of the given dimension.
| [in] | data_layout | The data layout. |
| [in] | data_layout_dimension | The dimension which this index is requested for. |
Definition at line 201 of file Helpers.inl.
References ARM_COMPUTE_ERROR_ON_MSG, arm_compute::cpu::data_layout, get_layout_map(), and UNKNOWN.
Referenced by calculate_same_pad(), calculate_valid_region_scale(), arm_compute::misc::shape_calculator::compute_col2im_shape(), arm_compute::misc::shape_calculator::compute_deconvolution_output_shape(), arm_compute::misc::shape_calculator::compute_deconvolution_padding(), arm_compute::misc::shape_calculator::compute_deconvolution_upsampled_shape(), arm_compute::misc::shape_calculator::compute_deep_convolution_shape(), arm_compute::misc::shape_calculator::compute_depth_to_space_shape(), arm_compute::misc::shape_calculator::compute_depthwise_convolution_shape(), arm_compute::misc::shape_calculator::compute_im2col_conv_shape(), arm_compute::misc::shape_calculator::compute_pool3d_shape(), arm_compute::misc::shape_calculator::compute_pool_shape(), arm_compute::misc::shape_calculator::compute_prior_box_shape(), arm_compute::misc::shape_calculator::compute_reorg_output_shape(), arm_compute::misc::shape_calculator::compute_roi_align_shape(), arm_compute::misc::shape_calculator::compute_space_to_batch_shape(), arm_compute::misc::shape_calculator::compute_space_to_depth_shape(), arm_compute::misc::shape_calculator::compute_unpool_shape(), arm_compute::misc::shape_calculator::compute_upsample_shape(), arm_compute::misc::shape_calculator::compute_vector_to_tensor_output_shape(), arm_compute::misc::shape_calculator::compute_winograd_filter_transform_shape(), arm_compute::misc::shape_calculator::compute_winograd_input_transform_shape(), arm_compute::misc::shape_calculator::compute_winograd_output_transform_shape(), CpuScale::configure(), ClPool2dKernel::configure(), ClPool3dKernel::configure(), ClScaleKernel::configure(), CpuConvertFullyConnectedWeightsKernel::configure(), ClConvertFullyConnectedWeightsKernel::configure(), CpuPool2dKernel::configure(), NEDepthToSpaceLayerKernel::configure(), CpuDirectConv2dKernel::configure(), ClWinogradInputTransformKernel::configure(), CLChannelShuffleLayerKernel::configure(), CpuPool3dKernel::configure(), CpuPool2d::configure(), ClWinogradOutputTransformKernel::configure(), CLSpaceToDepthLayerKernel::configure(), CLDepthToSpaceLayerKernel::configure(), CLSpaceToBatchLayerKernel::configure(), CLReorgLayerKernel::configure(), CLNormalizePlanarYUVLayerKernel::configure(), CpuScaleKernel::configure(), ClDirectConv2dKernel::configure(), NERNNLayer::configure(), NEScale::configure(), CLPriorBoxLayerKernel::configure(), CLROIAlignLayerKernel::configure(), ClIm2ColKernel::configure(), CpuIm2ColKernel::configure(), CLDeconvolutionReshapeOutputKernel::configure(), CLRNNLayer::configure(), CLDepthwiseConvolutionLayer::configure(), NEFFTConvolutionLayer::configure(), ClWinogradConv2d::configure(), NEGenerateProposalsLayer::configure(), CpuGemmConv2d::configure(), ClGemmConv2d::configure(), CLComputeMeanVariance::configure(), NEDeconvolutionLayer::configure(), CLFFTConvolutionLayer::configure(), CLGenerateProposalsLayer::configure(), CLGEMMDeconvolutionLayer::configure(), CLDirectDeconvolutionLayer::configure(), ROIAlignLayerNode::configure_output(), arm_compute::test::validation::reference::convert_fully_connected_weights(), SubTensorInfo::dimension(), TensorInfo::dimension(), IImageLoader::fill_planar_tensor(), ClConv2d::get_convolution_method(), CpuConv2d::get_convolution_method(), CLDeconvolutionLayer::get_deconvolution_method(), get_normalization_dimension_index(), CpuGemmConv2d::has_opt_impl(), CpuScale::prepare(), arm_compute::cpu::roi_align(), CPPUpsampleKernel::run(), NESpaceToDepthLayerKernel::run(), NEReorgLayerKernel::run(), CLDeconvolutionLayerUpsampleKernel::run(), CLROIAlignLayerKernel::run(), NESpaceToBatchLayerKernel::run(), CpuGemmConv2d::run(), arm_compute::cpu::kernels::run_im2col(), ClWinogradInputTransformKernel::run_op(), arm_compute::cl_dwc::use_cl_image_for_weights(), CpuScale::validate(), CpuPool2dKernel::validate(), CLDeconvolutionLayerUpsampleKernel::validate(), NERNNLayer::validate(), CLRNNLayer::validate(), ClComponentDirectConv2d::validate(), ClGemmConv2d::validate(), CpuGemmConv2d::validate(), CLDepthwiseConvolutionLayer::validate(), NEFFTConvolutionLayer::validate(), NEGenerateProposalsLayer::validate(), ClComponentDepthwiseConv2d::validate(), NEDeconvolutionLayer::validate(), CLFFTConvolutionLayer::validate(), CLGEMMDeconvolutionLayer::validate(), CLGenerateProposalsLayer::validate(), CLDirectDeconvolutionLayer::validate(), arm_compute::cpu::kernels::validate_arguments(), arm_compute::test::validation::reference::winograd_output_transform(), GpuCkwPool2d::write_component_code(), GpuCkwDepthwiseConv2d::write_component_code(), and GpuCkwDirectConv2d::write_component_code().
| std::string get_data_size_from_data_type | ( | const DataType & | dt | ) |
Get the size of a data type in number of bits.
| [in] | dt | DataType. |
Definition at line 194 of file CLHelpers.cpp.
References ARM_COMPUTE_ERROR, dt, F16, F32, QASYMM16, QASYMM8, QASYMM8_SIGNED, QSYMM16, QSYMM8, QSYMM8_PER_CHANNEL, S16, S32, S64, S8, U16, U32, U64, and U8.
Referenced by ClDirectConv2dKernel::configure(), CLROIPoolingLayerKernel::configure(), and CLROIAlignLayerKernel::configure().
| cl::NDRange get_default_lws_for_type | ( | CLKernelType | kernel_type, |
| cl::NDRange | gws | ||
| ) |
Definition at line 97 of file DefaultLWSHeuristics.cpp.
References CLKernelLibrary::default_ndrange(), DEPTHWISE, DIRECT, GEMM, CLKernelLibrary::get(), and WINOGRAD.
|
inline |
Get the DataLayoutDimension of a given index and layout.
| [in] | data_layout | The data layout. |
| [in] | index | The data layout index. |
Definition at line 212 of file Helpers.inl.
References ARM_COMPUTE_ERROR_ON_MSG, arm_compute::cpu::data_layout, get_layout_map(), and UNKNOWN.
|
inline |
Extract internal representation of a Context.
| [in] | ctx | Opaque context pointer |
Definition at line 127 of file IContext.h.
Referenced by AclActivation(), AclCreateQueue(), AclCreateTensor(), AclCreateTensorPack(), AclDestroyContext(), AclDestroyOperator(), AclDestroyQueue(), AclDestroyTensor(), AclDestroyTensorPack(), AclGetClContext(), AclGetClDevice(), AclGetClMem(), AclGetClQueue(), AclMapTensor(), AclPackTensor(), AclPackTensors(), AclQueueFinish(), AclRunOperator(), AclSetClContext(), AclSetClQueue(), AclTensorImport(), and AclUnmapTensor().
|
inline |
Extract internal representation of an Operator.
| [in] | op | Opaque operator pointer |
Definition at line 113 of file IOperator.h.
|
inline |
Extract internal representation of a TensoPack.
| [in] | pack | Opaque tensor pack pointer |
Definition at line 107 of file TensorPack.h.
References arm_compute::test::validation::pack.
| const std::map< DataLayout, std::vector< DataLayoutDimension > > & get_layout_map | ( | ) |
Returns a static map used to find an index or dimension based on a data layout.
*** Layouts ***
*** 4D *** [N C H W] [3 2 1 0] [N H W C]
Definition at line 107 of file Helpers.cpp.
References BATCHES, CHANNEL, DEPTH, HEIGHT, N, NCDHW, NCHW, NDHWC, NHWC, and WIDTH.
Referenced by get_data_layout_dimension_index(), and get_index_data_layout_dimension().
|
inline |
Compute the mininum and maximum values a data type can take.
| [in] | dt | Data type to get the min/max bounds of |
Definition at line 195 of file DataTypeUtils.h.
References ARM_COMPUTE_ERROR, BFLOAT16, dt, F16, F32, bfloat16::lowest(), arm_compute::support::cpp11::lowest(), bfloat16::max(), QASYMM16, QASYMM8, QASYMM8_SIGNED, QSYMM16, QSYMM8, QSYMM8_PER_CHANNEL, S16, S32, S8, U16, U32, and U8.
Referenced by ClPool2dKernel::configure(), ClPool3dKernel::configure(), ClGemmLowpOffsetContributionOutputStageKernel::configure(), ClGemmLowpMatrixMultiplyReshapedOnlyRhsKernel::configure(), ClGemmConv2d::configure(), get_quantized_activation_min_max(), arm_compute::quantization::get_quantized_asymmetric_output_min_max(), and CpuGemmLowpOffsetContributionOutputStageKernel::run_op().
|
inline |
Given an integer value, this function returns the next power of two.
| [in] | x | Input value |
Definition at line 74 of file Utils.h.
Referenced by ICLKernel::gws_from_window().
|
inline |
Calculate the normalization dimension index for a given normalization type.
| [in] | layout | Data layout of the input and output tensor |
| [in] | info | Normalization info |
Definition at line 39 of file NormalizationHelpers.h.
References CHANNEL, arm_compute::cpu::channel_idx, get_data_layout_dimension_index(), arm_compute::test::validation::info, WIDTH, and arm_compute::cpu::width_idx.
Referenced by NENormalizationLayerKernel::configure(), and CLNormalizationLayerKernel::configure().
| std::unordered_map< const ITensorInfo *, PaddingSize > get_padding_info | ( | std::initializer_list< const ITensor * > | tensors | ) |
Stores padding information before configuring a kernel.
| [in] | tensors | list of tensors to store the padding info for |
Definition at line 462 of file Utils.cpp.
References CLTensor::info(), TensorInfo::padding(), and tensor.
| std::unordered_map< const ITensorInfo *, PaddingSize > get_padding_info | ( | std::initializer_list< const ITensorInfo * > | infos | ) |
Stores padding information before configuring a kernel.
| [in] | infos | list of tensor infos to store the padding info for |
Definition at line 477 of file Utils.cpp.
References arm_compute::test::validation::info.
Referenced by ClDequantizeKernel::configure(), ClFloorKernel::configure(), ClReshapeKernel::configure(), ClTransposeKernel::configure(), ClCopyKernel::configure(), ClElementWiseUnaryKernel::configure(), ClWidthConcatenate2TensorsKernel::configure(), ClPool2dKernel::configure(), ClPool3dKernel::configure(), ClQuantizeKernel::configure(), ClScaleKernel::configure(), ClWidthConcatenateKernel::configure(), ClHeightConcatenateKernel::configure(), ClPermuteKernel::configure(), ClWidthConcatenate4TensorsKernel::configure(), ClActivationKernel::configure(), ClBatchConcatenateKernel::configure(), CLStridedSliceKernel::configure(), ClDepthConcatenateKernel::configure(), ClConvertFullyConnectedWeightsKernel::configure(), ClGemmLowpMatrixMultiplyNativeKernel::configure(), ClGemmReshapeLhsMatrixKernel::configure(), CLInstanceNormalizationLayerKernel::configure(), CLMaxUnpoolingLayerKernel::configure(), CLBitwiseKernel::configure(), ClGemmMatrixMultiplyNativeKernel::configure(), ClWinogradInputTransformKernel::configure(), ClWinogradFilterTransformKernel::configure(), ClGemmLowpQuantizeDownInt32ScaleByFixedPointKernel::configure(), CLChannelShuffleLayerKernel::configure(), ClGemmMatrixMultiplyReshapedOnlyRhsMMULKernel::configure(), CLSelectKernel::configure(), CLComputeAllAnchorsKernel::configure(), ClWinogradOutputTransformKernel::configure(), ClGemmLowpQuantizeDownInt32ScaleByFloatKernel::configure(), ClGemmLowpQuantizeDownInt32ScaleKernel::configure(), CLDeconvolutionLayerUpsampleKernel::configure(), CLSpaceToDepthLayerKernel::configure(), CLDepthToSpaceLayerKernel::configure(), CLNormalizationLayerKernel::configure(), CLQLSTMLayerNormalizationKernel::configure(), CLFFTScaleKernel::configure(), CLGatherKernel::configure(), CLSpaceToBatchLayerKernel::configure(), ClCastKernel::configure(), ClGemmLowpMatrixMultiplyReshapedKernel::configure(), CLBatchToSpaceLayerKernel::configure(), CLFFTDigitReverseKernel::configure(), ClGemmLowpMatrixMultiplyReshapedOnlyRhsMMULKernel::configure(), ClGemmLowpOffsetContributionOutputStageKernel::configure(), ClGemmLowpOffsetContributionKernel::configure(), CLReorgLayerKernel::configure(), CLNormalizePlanarYUVLayerKernel::configure(), CLReductionOperationKernel::configure(), CLReverseKernel::configure(), CLRangeKernel::configure(), CLFFTRadixStageKernel::configure(), CLL2NormalizeLayerKernel::configure(), ClGemmLowpMatrixMultiplyReshapedOnlyRhsKernel::configure(), CLPadLayerKernel::configure(), ClMulKernel::configure(), CLArgMinMaxLayerKernel::configure(), CLDepthwiseConvolutionLayerNativeKernel::configure(), CLBoundingBoxTransformKernel::configure(), ClGemmMatrixMultiplyReshapedOnlyRhsKernel::configure(), ClWeightsReshapeKernel::configure(), CLROIPoolingLayerKernel::configure(), ClGemmLowpMatrixAReductionKernel::configure(), ClIm2ColKernel::configure(), CLROIAlignLayerKernel::configure(), CLFillBorderKernel::configure(), ClGemmMatrixMultiplyReshapedKernel::configure(), CLDeconvolutionReshapeOutputKernel::configure(), CLFuseBatchNormalizationKernel::configure(), CLBatchNormalizationLayerKernel::configure(), CLComputeMeanVariance::configure(), ClComplexMulKernel::configure(), ClGemmLowpMatrixBReductionKernel::configure(), ClSaturatedArithmeticKernel::configure(), and ClArithmeticKernel::configure().
Return the promoted data type of a given data type.
| [in] | dt | Data type to get the promoted type of. |
Definition at line 159 of file DataTypeUtils.h.
References ARM_COMPUTE_ERROR, BFLOAT16, dt, F16, F32, QASYMM16, QASYMM8, QASYMM8_SIGNED, QSYMM16, QSYMM8, QSYMM8_PER_CHANNEL, S16, S32, S8, U16, U32, U8, and UNKNOWN.
| std::pair< int32_t, int32_t > get_quantized_activation_min_max | ( | const ActivationLayerInfo & | act_info, |
| DataType | data_type, | ||
| UniformQuantizationInfo | oq_info | ||
| ) |
Returns a pair of minimum and maximum values for a quantized activation.
| [in] | act_info | The information for activation |
| [in] | data_type | The used data type |
| [in] | oq_info | The output quantization information |
Definition at line 442 of file Utils.cpp.
References arm_compute::test::validation::act_info, arm_compute::test::validation::b, arm_compute::test::validation::data_type, get_min_max(), is_data_type_quantized_asymmetric_signed(), UniformQuantizationInfo::offset, quantize_qasymm8(), and quantize_qasymm8_signed().
Referenced by ClMatMulLowpNativeKernel::configure(), CLDepthwiseConvolutionLayerNativeKernel::configure(), ClGemmConv2d::configure(), and ClGemmConv2d::validate().
| QuantizationInfo get_softmax_output_quantization_info | ( | DataType | input_type, |
| bool | is_log | ||
| ) |
Returns output quantization information for softmax layer.
| [in] | input_type | The data type of the input tensor |
| [in] | is_log | True for log softmax |
Definition at line 421 of file Utils.cpp.
References is_data_type_quantized_asymmetric_signed().
Referenced by CpuSoftmaxKernel::configure(), SoftmaxLayerNode::configure_output(), and ClSoftmaxKernel::validate().
| GPUTarget get_target_from_device | ( | const cl::Device & | device | ) |
Helper function to get the GPU target from CL device.
| [in] | device | A CL device |
Definition at line 224 of file CLHelpers.cpp.
References get_target_from_name().
Referenced by CLCompileContext::default_ndrange(), CLScheduler::init(), and ICLKernel::set_target().
| GPUTarget get_target_from_name | ( | const std::string & | device_name | ) |
Helper function to get the GPU target from a device name.
| [in] | device_name | A device name |
Definition at line 188 of file GPUTarget.cpp.
References ARM_COMPUTE_LOG_INFO_MSG_CORE, BIFROST, MIDGARD, UNKNOWN, and VALHALL.
Referenced by CLDevice::CLDevice(), dot8_supported(), get_target_from_device(), and arm_compute::test::validation::TEST_CASE().
| bool get_wbsm_support_info | ( | const cl::Device & | device | ) |
Definition at line 429 of file CLHelpers.cpp.
References clGetDeviceInfo().
Referenced by CLCompileContext::CLCompileContext(), and CLCompileContext::set_device().
Variant of gpu_target_is_in for comparing two targets.
Definition at line 115 of file GPUTarget.h.
Helper function to check whether a gpu target is equal to the provided targets.
| [in] | target_to_check | gpu target to check |
| [in] | target | First target to compare against |
| [in] | targets | (Optional) Additional targets to compare with |
Definition at line 109 of file GPUTarget.h.
Referenced by arm_compute::test::validation::TEST_CASE().
| void handle_cl_error | ( | const std::string & | function_name, |
| cl_int | error_code | ||
| ) |
Check for CL error code and throw exception accordingly.
| [in] | function_name | The name of the CL function being called. |
| [in] | error_code | The error returned by the CL function. |
Definition at line 120 of file CLUtils.cpp.
References ARM_COMPUTE_ERROR, and to_string().
Referenced by CLMutableCommandBuffer::add_kernel(), CLMutableCommandBuffer::CLMutableCommandBuffer(), CLCompatCommandBuffer::enqueue(), CLMutableCommandBuffer::enqueue(), CLMutableCommandBuffer::finalize(), and CLMutableCommandBuffer::update().
|
inline |
Return true if the given format has horizontal subsampling.
| [in] | format | Format to determine subsampling. |
Definition at line 304 of file Validate.h.
References update_supported_ops::format, IYUV, NV12, NV21, UV88, UYVY422, and YUYV422.
Referenced by adjust_odd_shape(), and calculate_subsampled_shape().
|
inline |
Return true if the given format has vertical subsampling.
| [in] | format | Format to determine subsampling. |
Definition at line 318 of file Validate.h.
References update_supported_ops::format, IYUV, NV12, NV21, and UV88.
Referenced by adjust_odd_shape(), and calculate_subsampled_shape().
| bool has_holes | ( | const ITensorInfo & | info | ) |
Check if the tensor has any holes.
A hole is defined as any gap in the tensor between two consecutive values. This can be a result of extending the paddings or manipulating the strides of the tensor
| [in] | info | Tensor info object defining the shape of the input tensor. |
Definition at line 28 of file Utils.cpp.
References arm_compute::test::validation::info.
Referenced by CpuSoftmaxKernel::configure(), CpuReshapeKernel::prepare(), and NEStackLayerKernel::prepare().
| bool has_holes | ( | const ITensorInfo & | info, |
| size_t | dimension | ||
| ) |
Check if the tensor has any holes.
| [in] | info | Tensor info object defining the shape of the input tensor. |
| [in] | dimension | Highest dimension to check. |
Definition at line 33 of file Utils.cpp.
References arm_compute::test::validation::info, and arm_compute::test::validation::shape.
| 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.
| [in] | padding_map | an unordered map where each tensor info pointer is paired with its original padding info |
Definition at line 492 of file Utils.cpp.
Referenced by ClDequantizeKernel::configure(), ClFloorKernel::configure(), ClReshapeKernel::configure(), ClTransposeKernel::configure(), ClCopyKernel::configure(), ClElementWiseUnaryKernel::configure(), ClWidthConcatenate2TensorsKernel::configure(), ClPool2dKernel::configure(), ClPool3dKernel::configure(), ClQuantizeKernel::configure(), ClScaleKernel::configure(), ClWidthConcatenateKernel::configure(), ClHeightConcatenateKernel::configure(), ClPermuteKernel::configure(), ClWidthConcatenate4TensorsKernel::configure(), ClActivationKernel::configure(), ClBatchConcatenateKernel::configure(), CLStridedSliceKernel::configure(), ClDepthConcatenateKernel::configure(), ClConvertFullyConnectedWeightsKernel::configure(), ClGemmLowpMatrixMultiplyNativeKernel::configure(), ClGemmReshapeLhsMatrixKernel::configure(), CLInstanceNormalizationLayerKernel::configure(), CLBitwiseKernel::configure(), CLMaxUnpoolingLayerKernel::configure(), ClGemmMatrixMultiplyNativeKernel::configure(), ClWinogradFilterTransformKernel::configure(), ClWinogradInputTransformKernel::configure(), ClGemmLowpQuantizeDownInt32ScaleByFixedPointKernel::configure(), ClGemmMatrixMultiplyReshapedOnlyRhsMMULKernel::configure(), CLChannelShuffleLayerKernel::configure(), CLSelectKernel::configure(), CLComputeAllAnchorsKernel::configure(), ClWinogradOutputTransformKernel::configure(), ClGemmLowpQuantizeDownInt32ScaleByFloatKernel::configure(), ClGemmLowpQuantizeDownInt32ScaleKernel::configure(), CLDeconvolutionLayerUpsampleKernel::configure(), CLSpaceToDepthLayerKernel::configure(), CLDepthToSpaceLayerKernel::configure(), CLNormalizationLayerKernel::configure(), CLQLSTMLayerNormalizationKernel::configure(), CLFFTScaleKernel::configure(), CLGatherKernel::configure(), CLSpaceToBatchLayerKernel::configure(), ClCastKernel::configure(), ClGemmLowpMatrixMultiplyReshapedKernel::configure(), CLBatchToSpaceLayerKernel::configure(), CLFFTDigitReverseKernel::configure(), ClGemmLowpOffsetContributionKernel::configure(), ClGemmLowpOffsetContributionOutputStageKernel::configure(), CLReorgLayerKernel::configure(), CLNormalizePlanarYUVLayerKernel::configure(), CLRangeKernel::configure(), CLReductionOperationKernel::configure(), CLReverseKernel::configure(), CLFFTRadixStageKernel::configure(), ClGemmLowpMatrixMultiplyReshapedOnlyRhsKernel::configure(), CLL2NormalizeLayerKernel::configure(), CLPadLayerKernel::configure(), ClMulKernel::configure(), CLArgMinMaxLayerKernel::configure(), CLDepthwiseConvolutionLayerNativeKernel::configure(), CLBoundingBoxTransformKernel::configure(), ClGemmMatrixMultiplyReshapedOnlyRhsKernel::configure(), ClWeightsReshapeKernel::configure(), CLROIPoolingLayerKernel::configure(), ClIm2ColKernel::configure(), ClGemmLowpMatrixAReductionKernel::configure(), CLROIAlignLayerKernel::configure(), CLFillBorderKernel::configure(), ClGemmMatrixMultiplyReshapedKernel::configure(), CLDeconvolutionReshapeOutputKernel::configure(), CLFuseBatchNormalizationKernel::configure(), CLBatchNormalizationLayerKernel::configure(), CLComputeMeanVariance::configure(), ClComplexMulKernel::configure(), ClGemmLowpMatrixBReductionKernel::configure(), ClSaturatedArithmeticKernel::configure(), and ClArithmeticKernel::configure().
|
inline |
| bool image2d_from_buffer_supported | ( | const cl::Device & | device | ) |
Helper function to check whether the cl_khr_image2d_from_buffer extension is supported.
| [in] | device | A CL device |
Definition at line 377 of file CLHelpers.cpp.
References device_supports_extension().
Referenced by create_image2d_from_buffer(), export_to_cl_image(), arm_compute::test::validation::TEST_CASE(), and arm_compute::opencl::kernels::gemm::validate_image2d_support_on_rhs().
|
inline |
Convert a linear index into n-dimensional coordinates.
| [in] | shape | Shape of the n-dimensional tensor. |
| [in] | index | Linear index specifying the i-th element. |
Definition at line 164 of file Helpers.inl.
References ARM_COMPUTE_ERROR_ON_MSG, and arm_compute::test::validation::shape.
Referenced by arm_compute::test::validation::reference::convert_fully_connected_weights().
|
inline |
| ValidRegion arm_compute::intersect_valid_regions | ( | const Ts &... | regions | ) |
Intersect multiple valid regions.
| [in] | regions | Valid regions. |
Definition at line 64 of file WindowHelpers.h.
References ValidRegion::anchor, arm_compute::utility::foldl(), Dimensions< T >::num_dimensions(), Dimensions< T >::set(), TensorShape::set(), and ValidRegion::shape.
|
inline |
Check if a given data type is of floating point type.
| [in] | dt | Input data type. |
Definition at line 304 of file DataTypeUtils.h.
Referenced by ClPool2dKernel::configure(), ClQuantizeKernel::configure(), ClScaleKernel::configure(), ClDirectConv2d::configure(), ClCastKernel::configure(), CLReductionOperationKernel::configure(), CLArgMinMaxLayerKernel::configure(), ClMulKernel::configure(), export_to_cl_image(), arm_compute::graph::detail::fuse_node_with_activation(), ClConv2d::get_convolution_method(), ClPool2dKernel::run_op(), ClSaturatedArithmeticKernel::validate(), and ClArithmeticKernel::validate().
|
inline |
Check if a given data type is of quantized type.
| [in] | dt | Input data type. |
Definition at line 324 of file DataTypeUtils.h.
References dt, QASYMM16, QASYMM8, QASYMM8_SIGNED, QSYMM16, QSYMM8, and QSYMM8_PER_CHANNEL.
Referenced by arm_compute::test::validation::reference::arithmetic_operation(), CpuAddMulAdd::configure(), ClTransposedConvolutionKernel::configure(), ClElementWiseUnaryKernel::configure(), ClPool2dKernel::configure(), ClPool3dKernel::configure(), ClActivationKernel::configure(), CLComputeAllAnchorsKernel::configure(), CPPDetectionPostProcessLayer::configure(), ClCastKernel::configure(), CLComparisonKernel::configure(), CpuMatMul::configure(), CLNormalizePlanarYUVLayerKernel::configure(), CLReductionOperationKernel::configure(), ClDirectConv2dKernel::configure(), CpuGemmDirectConv2d::configure(), ClDirectConv3dKernel::configure(), ClMulKernel::configure(), CLBoundingBoxTransformKernel::configure(), CLReduceMean::configure(), CLDepthwiseConvolutionLayerNativeKernel::configure(), NEDetectionPostProcessLayer::configure(), CLDepthwiseConvolutionLayer::configure(), error_on_mismatching_quantization_info(), needs_serialized_reduction(), operator<<(), QuantizationLayerNode::QuantizationLayerNode(), CpuAddMulAdd::run(), arm_compute::cpu::kernels::run_im2col(), arm_compute::test::validation::reference::space_to_batch(), CpuAddMulAdd::validate(), CpuMatMul::validate(), CpuDepthwiseConv2dAssemblyWrapperKernel::validate(), CpuFullyConnected::validate(), NEDetectionPostProcessLayer::validate(), ClFullyConnected::validate(), CLDepthwiseConvolutionLayer::validate(), NEDeconvolutionLayer::validate(), and NEConvolutionLayer::validate().
|
inline |
Check if a given data type is of asymmetric quantized type.
| [in] | dt | Input data type. |
Definition at line 346 of file DataTypeUtils.h.
References dt, QASYMM16, QASYMM8, and QASYMM8_SIGNED.
Referenced by GraphBuilder::add_convolution_node(), GraphBuilder::add_deconvolution_node(), GraphBuilder::add_depthwise_convolution_node(), GraphBuilder::add_fully_connected_layer(), ClDequantizeKernel::configure(), ClWidthConcatenate2TensorsKernel::configure(), ClPool2dKernel::configure(), ClPool3dKernel::configure(), ClWidthConcatenateKernel::configure(), ClHeightConcatenateKernel::configure(), ClQuantizeKernel::configure(), ClScaleKernel::configure(), ClWidthConcatenate4TensorsKernel::configure(), ClActivationKernel::configure(), CpuSoftmaxKernel::configure(), ClBatchConcatenateKernel::configure(), ClDepthConcatenateKernel::configure(), ClDirectConv2d::configure(), CpuSoftmaxGeneric::configure(), CLRangeKernel::configure(), ClMulKernel::configure(), CLROIPoolingLayerKernel::configure(), CLROIAlignLayerKernel::configure(), CpuFullyConnected::configure(), ClFullyConnected::configure(), CpuGemmConv2d::configure(), ClGemmConv2d::configure(), CpuGemmLowpMatrixMultiplyCore::configure(), CLGEMMDeconvolutionLayer::configure(), arm_compute::graph::backends::detail::create_concatenate_layer(), arm_compute::graph::backends::detail::create_convolution_layer(), arm_compute::graph::backends::detail::create_depthwise_convolution_layer(), arm_compute::graph::backends::detail::create_fully_connected_layer(), arm_compute::test::validation::reference::im2col_nchw(), arm_compute::test::validation::reference::im2col_nhwc(), arm_compute::cpu::roi_align(), CpuGemmLowpMatrixMultiplyCore::run(), CpuSoftmaxKernel::run_op(), set_quantization_info_if_empty(), ClSoftmaxKernel::validate(), CpuSoftmaxGeneric::validate(), CpuGemmDirectConv2d::validate(), ClGemmLowpMatrixMultiplyCore::validate(), ClGemmConv2d::validate(), CpuGemmConv2d::validate(), CpuGemmLowpMatrixMultiplyCore::validate(), NEDeconvolutionLayer::validate(), CLGEMMDeconvolutionLayer::validate(), CLDirectDeconvolutionLayer::validate(), and arm_compute::graph::backends::detail::validate_convolution_layer().
|
inline |
Check if a given data type is of 8-bit asymmetric quantized signed type.
| [in] | dt | Input data type. |
Definition at line 382 of file DataTypeUtils.h.
References dt, QASYMM8, and QASYMM8_SIGNED.
Referenced by CpuQuantizeKernel::configure().
|
inline |
Check if a given data type is of asymmetric quantized signed type.
| [in] | dt | Input data type. |
Definition at line 365 of file DataTypeUtils.h.
References dt, and QASYMM8_SIGNED.
Referenced by CpuDirectConv2dOutputStageKernel::configure(), get_quantized_activation_min_max(), get_softmax_output_quantization_info(), and arm_compute::cpu::roi_align_1x1_qasymm8().
|
inline |
Check if a given data type is of per channel type.
| [in] | dt | Input data type. |
Definition at line 419 of file DataTypeUtils.h.
References dt, and QSYMM8_PER_CHANNEL.
Referenced by CLTensorAllocator::allocate(), ClDequantizeKernel::configure(), CpuDepthwiseConv2dAssemblyWrapperKernel::configure(), CLDepthwiseConvolutionLayer::configure(), ClGemmLowpMatrixMultiplyCore::configure(), ClGemmConv2d::configure(), CpuGemmLowpMatrixMultiplyCore::configure(), arm_compute::test::validation::reference::dequantization_layer(), CLDeconvolutionLayer::get_deconvolution_method(), arm_compute::cpu::run_depthwise_quanitized8bit(), ClDequantizeKernel::run_op(), CpuDepthwiseConv2dAssemblyWrapperKernel::validate(), ClGemmLowpMatrixMultiplyCore::validate(), ClGemmConv2d::validate(), CLDepthwiseConvolutionLayer::validate(), CpuGemmLowpMatrixMultiplyCore::validate(), NEDeconvolutionLayer::validate(), and CpuGemmAssemblyDispatch::validate().
|
inline |
Check if a given data type is of symmetric quantized type.
| [in] | dt | Input data type. |
Definition at line 400 of file DataTypeUtils.h.
References dt, QSYMM16, QSYMM8, and QSYMM8_PER_CHANNEL.
Referenced by ClGemmLowpMatrixMultiplyCore::configure(), and ClGemmLowpMatrixMultiplyCore::validate().
|
inline |
Definition at line 1660 of file Types.h.
References ANY, and UNSPECIFIED.
Referenced by CpuGemmDirectConv2d::validate(), and CpuGemmConv2d::validate().
|
inline |
Definition at line 1664 of file Types.h.
Referenced by CpuMatMul::configure(), CpuFullyConnected::validate(), CpuGemm::validate(), and CpuGemmAssemblyDispatch::validate().
| bool is_pool_3d_region_entirely_outside_input | ( | const Pooling3dLayerInfo & | info | ) |
Check if the 3d pool region is entirely outside the input tensor.
| [in] | info | Pooling3dLayerInfo to be checked. |
Definition at line 141 of file Utils.cpp.
References arm_compute::test::validation::info.
| bool is_pool_region_entirely_outside_input | ( | const PoolingLayerInfo & | info | ) |
Check if the pool region is entirely outside the input tensor.
| [in] | info | PoolingLayerInfo to be checked. |
Definition at line 129 of file Utils.cpp.
References arm_compute::test::validation::info.
Referenced by CpuPool2dAssemblyWrapperKernel::validate(), and ClComponentPool2d::validate().
|
inline |
Check if the 3D padding is symmetric i.e.
padding in each opposite sides are euqal (left=right, top=bottom and front=back)
| [in] | info | Padding3D input 3D padding object to check if it is symmetric |
Definition at line 245 of file Utils.h.
References arm_compute::test::validation::info.
| std::string join | ( | const std::vector< std::string > | strings, |
| const std::string & | sep | ||
| ) |
Join a sequence of strings with separator sep.
| [in] | strings | Strings to join |
| [in] | sep | Separator to join consecutive strings in the sequence |
Definition at line 66 of file StringUtils.cpp.
References arm_compute::test::validation::reference::accumulate(), and arm_compute::test::validation::b.
Referenced by GEMMParam::__str__(), NativeGEMMConfig::__str__(), ReshapedOnlyRHSGEMMConfig::__str__(), ReshapedGEMMConfig::__str__(), Measurement::__str__(), format_code::check_copyright(), format_code::check_license(), check_header_guards::find_expected_header_guard(), GpuCkwElementwiseBinary::get_name(), format_doxygen::process_comment(), format_code::run_fix_code_formatting(), and GEMMBenchmarkResultRecorder::summary().
| std::string lower_string | ( | const std::string & | val | ) |
Lower a given string.
| [in] | val | Given string to lower. |
Definition at line 38 of file StringUtils.cpp.
References arm_compute::utility::tolower().
Referenced by ClTransposedConvolutionKernel::configure(), ClMatMulLowpNativeMMULKernel::configure(), ClWidthConcatenate2TensorsKernel::configure(), ClPool2dKernel::configure(), ClPool3dKernel::configure(), ClScaleKernel::configure(), ClActivationKernel::configure(), ClWidthConcatenate4TensorsKernel::configure(), ClMatMulNativeKernel::configure(), CLStridedSliceKernel::configure(), ClMatMulLowpNativeKernel::configure(), ClGemmReshapeLhsMatrixKernel::configure(), CLMaxUnpoolingLayerKernel::configure(), ClGemmMatrixMultiplyNativeKernel::configure(), ClGemmMatrixMultiplyReshapedOnlyRhsMMULKernel::configure(), ClWinogradInputTransformKernel::configure(), CLChannelShuffleLayerKernel::configure(), ClWinogradFilterTransformKernel::configure(), ClIndirectConv2dKernel::configure(), ClWinogradOutputTransformKernel::configure(), CLQLSTMLayerNormalizationKernel::configure(), CLFFTScaleKernel::configure(), CLSpaceToDepthLayerKernel::configure(), ClSoftmaxKernel::configure(), CLDepthToSpaceLayerKernel::configure(), CLNormalizationLayerKernel::configure(), CLTileKernel::configure(), CLSpaceToBatchLayerKernel::configure(), CLComparisonKernel::configure(), ClCastKernel::configure(), CLFFTDigitReverseKernel::configure(), CLReorgLayerKernel::configure(), CLMeanStdDevNormalizationKernel::configure(), CLBatchToSpaceLayerKernel::configure(), CLNormalizePlanarYUVLayerKernel::configure(), CLRangeKernel::configure(), CLReverseKernel::configure(), CLFFTRadixStageKernel::configure(), ClCol2ImKernel::configure(), ClDirectConv2dKernel::configure(), ClDirectConv3dKernel::configure(), ClMatMulNativeMMULKernel::configure(), ClMulKernel::configure(), ClGemmMatrixMultiplyReshapedOnlyRhsKernel::configure(), CLDepthwiseConvolutionLayerNativeKernel::configure(), ClIm2ColKernel::configure(), CLFillBorderKernel::configure(), ClGemmMatrixMultiplyReshapedKernel::configure(), CLDeconvolutionReshapeOutputKernel::configure(), CLBatchNormalizationLayerKernel::configure(), ClComplexMulKernel::configure(), arm_compute::graph_utils::get_input_accessor(), and GpuCkwElementwiseBinary::get_name().
| WorkspaceData<TensorType> arm_compute::manage_workspace | ( | const experimental::MemoryRequirements & | mem_reqs, |
| MemoryGroup & | mgroup, | ||
| ITensorPack & | run_pack | ||
| ) |
Definition at line 56 of file MemoryHelpers.h.
| WorkspaceData<TensorType> arm_compute::manage_workspace | ( | const experimental::MemoryRequirements & | mem_reqs, |
| MemoryGroup & | mgroup, | ||
| ITensorPack & | run_pack, | ||
| ITensorPack & | prep_pack | ||
| ) |
Definition at line 63 of file MemoryHelpers.h.
References ITensorPack::add_tensor(), CLTensorAllocator::allocate(), CLTensor::allocator(), ARM_COMPUTE_ERROR_ON_NULLPTR, MemoryGroup::manage(), WorkspaceDataElement< TensorType >::slot, arm_compute::experimental::Temporary, tensor, and U8.
|
inline |
Multiply a neon vector using quantized multiplier and shift.
| [in] | input | Input vector to mutiply values to be quantized. |
| [in] | qmul | Quantized multipler |
| [in] | shift | Left bit shift |
Definition at line 225 of file NESymm.h.
References arm_compute::test::validation::input, and rounding_divide_by_pow2().
| bool needs_serialized_reduction | ( | ReductionOperation | op, |
| DataType | dt, | ||
| unsigned int | axis | ||
| ) |
Check if the given reduction operation should be handled in a serial way.
| [in] | op | Reduction operation to perform |
| [in] | dt | Data type |
| [in] | axis | Axis along which to reduce |
Definition at line 412 of file Utils.cpp.
References dt, is_data_type_quantized(), MAX, and MIN.
Referenced by CLReductionOperationKernel::configure(), and CLReductionOperationKernel::run().
| void arm_compute::normalize_float | ( | const Window & | window, |
| const ITensor * | in, | ||
| const ITensor * | in_squared, | ||
| ITensor * | out, | ||
| NormalizationLayerInfo | ninfo | ||
| ) |
Function to perform normalization depending on the given template dimension.
The second template parameter specifies whether the normalization has to be 1D or 2D.
| [in] | window | Region on which to execute the kernel. |
| [in] | in | Source tensor. 3 lower dims represent a single input with dimensions [width, height, IFM], and an optional 4th dimension for batch of inputs. Data types supported: FP16/F32. Data layouts supported: NCHW/NHWC. |
| [in] | in_squared | Source with each element has been squared. 3 lower dims represent a single input with dimensions [width, height, IFM], Data type and layout supported: same as input. |
| [in] | out | Destination tensor. Output will have the same number of dimensions as input. Data type and layout supported: same as input. |
| [in] | ninfo | Normalization layer information like the normalization type, normalization size and other parameters. |
SIMD vector tag type.
Definition at line 58 of file impl.h.
References NormalizationLayerInfo::beta(), ITensorInfo::data_layout(), ITensorInfo::dimension(), Window::DimX, Window::Dimension::end(), execute_window_loop(), ITensor::info(), arm_compute::test::validation::input, NormalizationLayerInfo::kappa(), NCHW, NormalizationLayerInfo::norm_size(), Iterator::ptr(), NormalizationLayerInfo::scale_coeff(), Window::set(), Window::Dimension::start(), ITensorInfo::strides_in_bytes(), arm_compute::wrapper::vadd(), arm_compute::wrapper::vdup_n(), arm_compute::wrapper::vinv(), arm_compute::wrapper::vloadq(), arm_compute::wrapper::vmla(), arm_compute::wrapper::vmul(), arm_compute::wrapper::vpow(), arm_compute::wrapper::vstore(), and Window::x().
|
inline |
Return the number of channels for a given single-planar pixel format.
| [in] | format | Input format |
Definition at line 302 of file FormatUtils.h.
References BFLOAT16, F16, F32, update_supported_ops::format, IYUV, NV12, NV21, RGB888, RGBA8888, S16, S32, U16, U32, U8, UV88, UYVY422, YUV444, and YUYV422.
Referenced by TensorInfo::init(), TensorInfo::init_auto_padding(), and TensorInfo::set_format().
|
inline |
Returns the number of elements required to go from start to end with the wanted step.
| [in] | start | start value |
| [in] | end | end value |
| [in] | step | step value between each number in the wanted sequence |
Definition at line 295 of file Utils.h.
References ARM_COMPUTE_ERROR_ON_MSG, arm_compute::mlgo::parser::end(), and arm_compute::cpu::step.
Referenced by NERangeKernel::configure().
|
inline |
Return the number of planes for a given format.
| [in] | format | Input format |
Definition at line 267 of file FormatUtils.h.
References ARM_COMPUTE_ERROR, BFLOAT16, F16, F32, update_supported_ops::format, IYUV, NV12, NV21, RGB888, RGBA8888, S16, S32, U16, U32, U8, UYVY422, YUV444, and YUYV422.
|
inline |
Definition at line 38 of file MemoryHelpers.h.
References ACL_INT_VEC, and offset().
Referenced by CpuAddMulAdd::configure(), ClSoftmax::configure(), CpuSoftmaxGeneric::configure(), CpuMatMul::configure(), CpuGemmDirectConv2d::configure(), CpuWinogradConv2d::configure(), CpuFullyConnected::configure(), ClFullyConnected::configure(), ClGemmLowpMatrixMultiplyCore::configure(), ClWinogradConv2d::configure(), CpuGemmConv2d::configure(), ClGemmConv2d::configure(), CpuGemmLowpMatrixMultiplyCore::configure(), CpuGemmDirectConv2d::prepare(), CpuWinogradConv2d::prepare(), ClFullyConnected::prepare(), ClGemmLowpMatrixMultiplyCore::prepare(), ClGemm::prepare(), ClWinogradConv2d::prepare(), CpuFullyConnected::prepare(), ClGemmConv2d::prepare(), CpuGemmLowpMatrixMultiplyCore::prepare(), CpuGemmConv2d::prepare(), ClSoftmax::run(), CpuAddMulAdd::run(), CpuSoftmaxGeneric::run(), CpuMatMul::run(), CpuWinogradConv2d::run(), ClIndirectConv2d::run(), ClFullyConnected::run(), ClGemmLowpMatrixMultiplyCore::run(), ClGemm::run(), ClWinogradConv2d::run(), CpuFullyConnected::run(), ClGemmConv2d::run(), CpuGemmLowpMatrixMultiplyCore::run(), CpuGemm::run(), and CpuGemmConv2d::run().
| bool opencl_is_available | ( | ) |
Check if OpenCL is available.
Definition at line 236 of file OpenCL.cpp.
References CLSymbols::clBuildProgram_ptr, clGetPlatformIDs(), CLSymbols::get(), and CLSymbols::load_default().
Referenced by create_opencl_context_and_device(), CLScheduler::get(), CLDeviceBackend::is_backend_supported(), main(), Framework::run(), and arm_compute::test::sync_if_necessary().
|
inline |
Check that given dimensions are not equal.
| [in] | lhs | Left-hand side Dimensions. |
| [in] | rhs | Right-hand side Dimensions. |
Definition at line 287 of file Dimensions.h.
|
inline |
Check whether two quantization info are not equal.
| [in] | lhs | RHS quantization info. |
| [in] | rhs | LHS quantization info. |
Definition at line 187 of file QuantizationInfo.h.
References operator==().
|
inline |
Check whether two quantization info are not equal.
| [in] | lhs | RHS quantization info. |
| [in] | rhs | LHS quantization info. |
Definition at line 211 of file QuantizationInfo.h.
References operator==().
| inline ::std::ostream& arm_compute::operator<< | ( | ::std::ostream & | os, |
| const ActivationLayerInfo * | info | ||
| ) |
Formatted output of the activation function info.
| [out] | os | Output stream. |
| [in] | info | ActivationLayerInfo to output. |
Definition at line 544 of file TypePrinter.h.
References arm_compute::test::validation::info.
| inline ::std::ostream& arm_compute::operator<< | ( | ::std::ostream & | os, |
| const ActivationLayerInfo::ActivationFunction & | act_function | ||
| ) |
Formatted output of the activation function type.
| [out] | os | Output stream. |
| [in] | act_function | Type to output. |
Definition at line 461 of file TypePrinter.h.
References ARM_COMPUTE_ERROR.
| inline ::std::ostream& arm_compute::operator<< | ( | ::std::ostream & | os, |
| const ArithmeticOperation & | op | ||
| ) |
Formatted output of the ArithmeticOperation type.
| [out] | os | Output stream. |
| [in] | op | Operation to output. |
Definition at line 1747 of file TypePrinter.h.
References ADD, ARM_COMPUTE_ERROR, DIV, MAX, MIN, POWER, PRELU, SQUARED_DIFF, and SUB.
| inline ::std::ostream& arm_compute::operator<< | ( | ::std::ostream & | os, |
| const arm_compute::CpuMatMulSettings & | settings | ||
| ) |
Formatted output of the arm_compute::CpuMatMulSettings type.
| [out] | os | Output stream. |
| [in] | settings | arm_compute::CpuMatMulSettings type to output. |
Definition at line 3601 of file TypePrinter.h.
References CpuMatMulSettings::fast_math(), and CpuMatMulSettings::fixed_format().
| inline ::std::ostream& arm_compute::operator<< | ( | ::std::ostream & | os, |
| const arm_compute::MatMulInfo & | matmul_info | ||
| ) |
Formatted output of the arm_compute::MatMulInfo type.
| [out] | os | Output stream. |
| [in] | matmul_info | arm_compute::MatMulInfo type to output. |
Definition at line 3540 of file TypePrinter.h.
References MatMulInfo::adj_lhs(), and MatMulInfo::adj_rhs().
| inline ::std::ostream& arm_compute::operator<< | ( | ::std::ostream & | os, |
| const arm_compute::MatMulKernelInfo & | matmul_info | ||
| ) |
Formatted output of the arm_compute::MatMulKernelInfo type.
| [out] | os | Output stream. |
| [in] | matmul_info | arm_compute::MatMulKernelInfo type to output. |
Definition at line 3568 of file TypePrinter.h.
References MatMulKernelInfo::adj_lhs, MatMulKernelInfo::adj_rhs, MatMulKernelInfo::export_rhs_to_cl_image, MatMulKernelInfo::k0, MatMulKernelInfo::m0, and MatMulKernelInfo::n0.
| inline ::std::ostream& arm_compute::operator<< | ( | ::std::ostream & | os, |
| const arm_compute::ScatterInfo & | info | ||
| ) |
Formatted output of the arm_compute::ScatterInfo type.
| [out] | os | Output stream. |
| [in] | info | arm_compute::ScatterInfo type to output. |
Definition at line 3672 of file TypePrinter.h.
References arm_compute::test::validation::info.
| inline ::std::ostream& arm_compute::operator<< | ( | ::std::ostream & | os, |
| const arm_compute::WeightFormat & | wf | ||
| ) |
Formatted output of the arm_compute::WeightFormat type.
| [out] | os | Output stream. |
| [in] | wf | WeightFormat to output. |
Definition at line 3242 of file TypePrinter.h.
References to_string().
| inline ::std::ostream& arm_compute::operator<< | ( | ::std::ostream & | os, |
| const BorderMode & | mode | ||
| ) |
Formatted output of the BorderMode type.
| [out] | os | Output stream. |
| [in] | mode | Type to output. |
Definition at line 1015 of file TypePrinter.h.
References ARM_COMPUTE_ERROR, CONSTANT, clang_tidy_rules::mode, REPLICATE, and UNDEFINED.
| inline ::std::ostream& arm_compute::operator<< | ( | ::std::ostream & | os, |
| const BorderSize & | border | ||
| ) |
Formatted output of the BorderSize type.
| [out] | os | Output stream. |
| [in] | border | Type to output. |
Definition at line 1042 of file TypePrinter.h.
References BorderSize::bottom, BorderSize::left, BorderSize::right, and BorderSize::top.
| inline ::std::ostream& arm_compute::operator<< | ( | ::std::ostream & | os, |
| const BoundingBoxTransformInfo & | bbox_info | ||
| ) |
Formatted output of the BoundingBoxTransformInfo type.
| [out] | os | Output stream. |
| [in] | bbox_info | Type to output. |
Definition at line 346 of file TypePrinter.h.
References BoundingBoxTransformInfo::img_height(), BoundingBoxTransformInfo::img_width(), BoundingBoxTransformInfo::scale(), and BoundingBoxTransformInfo::weights().
| inline ::std::ostream& arm_compute::operator<< | ( | ::std::ostream & | os, |
| const BoxNMSLimitInfo & | info | ||
| ) |
Formatted output of the BoxNMSLimitInfo type.
| [out] | os | Output stream. |
| [in] | info | BoxNMSLimitInfo to output. |
Definition at line 3103 of file TypePrinter.h.
References arm_compute::test::validation::info.
| inline ::std::ostream& arm_compute::operator<< | ( | ::std::ostream & | os, |
| const Channel & | channel | ||
| ) |
| inline ::std::ostream& arm_compute::operator<< | ( | ::std::ostream & | os, |
| const ClComponentElementwiseBinary::Attributes::ElementwiseOp & | op | ||
| ) |
Formatted output of the pute::experimental::dynamic_fusion::ClComponentElementwiseBinary::Attributes::ElementwiseOp type.
| [out] | os | Output stream. |
| [in] | op | arm_compute::experimental::dynamic_fusion::ClComponentElementwiseBinary::Attributes::ElementwiseOp type to output. |
Definition at line 47 of file ElementwiseBinary.h.
References ElementwiseBinaryCommonAttributes::Add, ElementwiseBinaryCommonAttributes::Div, ElementwiseBinaryCommonAttributes::Max, ElementwiseBinaryCommonAttributes::Min, ElementwiseBinaryCommonAttributes::Mul, ElementwiseBinaryCommonAttributes::Power, ElementwiseBinaryCommonAttributes::Prelu, ElementwiseBinaryCommonAttributes::SquaredDiff, and ElementwiseBinaryCommonAttributes::Sub.
| inline ::std::ostream& arm_compute::operator<< | ( | ::std::ostream & | os, |
| const CLTunerMode & | val | ||
| ) |
[Print CLTunerMode type]
Formatted output of the CLTunerMode type.
| [out] | os | Output stream. |
| [in] | val | CLTunerMode to output. |
Definition at line 2578 of file TypePrinter.h.
References to_string().
| inline ::std::ostream& arm_compute::operator<< | ( | ::std::ostream & | os, |
| const ComparisonOperation & | op | ||
| ) |
Formatted output of the Comparison Operations.
| [out] | os | Output stream. |
| [in] | op | Type to output. |
Definition at line 1857 of file TypePrinter.h.
References ARM_COMPUTE_ERROR, Equal, Greater, GreaterEqual, Less, LessEqual, and NotEqual.
| inline ::std::ostream& arm_compute::operator<< | ( | ::std::ostream & | os, |
| const ComputeAnchorsInfo & | anchors_info | ||
| ) |
Formatted output of the ComputeAnchorsInfo type.
| [out] | os | Output stream. |
| [in] | anchors_info | Type to output. |
Definition at line 381 of file TypePrinter.h.
References ComputeAnchorsInfo::feat_height(), ComputeAnchorsInfo::feat_width(), and ComputeAnchorsInfo::spatial_scale().
| inline ::std::ostream& arm_compute::operator<< | ( | ::std::ostream & | os, |
| const Conv2dInfo & | conv_info | ||
| ) |
Formatted output of the Conv2dInfo type.
| [out] | os | Output stream. |
| [in] | conv_info | Conv2dInfo to output. |
Definition at line 2729 of file TypePrinter.h.
References arm_compute::test::validation::conv_info, and to_string().
| inline ::std::ostream& arm_compute::operator<< | ( | ::std::ostream & | os, |
| const Conv3dInfo & | conv3d_info | ||
| ) |
Formatted output of the Conv3dInfo type.
| [out] | os | Output stream. |
| [in] | conv3d_info | Type to output. |
Definition at line 3150 of file TypePrinter.h.
References Conv3dInfo::act_info, Conv3dInfo::dilation, Conv3dInfo::enable_fast_math, Conv3dInfo::padding, Conv3dInfo::round_type, Conv3dInfo::stride, and to_string().
| inline ::std::ostream& arm_compute::operator<< | ( | ::std::ostream & | os, |
| const ConvertPolicy & | policy | ||
| ) |
Formatted output of the ConvertPolicy type.
| [out] | os | Output stream. |
| [in] | policy | Type to output. |
Definition at line 1716 of file TypePrinter.h.
References ARM_COMPUTE_ERROR, SATURATE, and WRAP.
| inline ::std::ostream& arm_compute::operator<< | ( | ::std::ostream & | os, |
| const ConvolutionInfo & | conv_info | ||
| ) |
Formatted output of the ConvolutionInfo type.
| [out] | os | Output stream. |
| [in] | conv_info | ConvolutionInfo to output. |
Definition at line 2591 of file TypePrinter.h.
References arm_compute::test::validation::conv_info, and to_string().
| inline ::std::ostream& arm_compute::operator<< | ( | ::std::ostream & | os, |
| const ConvolutionMethod & | conv_method | ||
| ) |
Formatted output of the ConvolutionMethod type.
| [out] | os | Output stream |
| [in] | conv_method | Type to output |
Definition at line 2169 of file TypePrinter.h.
References ARM_COMPUTE_ERROR, DIRECT, FFT, GEMM, GEMM_CONV2D, and WINOGRAD.
| inline ::std::ostream& arm_compute::operator<< | ( | ::std::ostream & | os, |
| const Coordinates2D & | coord_2d | ||
| ) |
Formatted output of the Coordinates2D type.
| [out] | os | Output stream. |
| [in] | coord_2d | Coordinates2D to output. |
Definition at line 2909 of file TypePrinter.h.
References Coordinates2D::x, and Coordinates2D::y.
| inline ::std::ostream& arm_compute::operator<< | ( | ::std::ostream & | os, |
| const DataLayout & | data_layout | ||
| ) |
[Print DataLayout type]
Formatted output of the DataLayout type.
| [out] | os | Output stream. |
| [in] | data_layout | Type to output. |
Definition at line 696 of file TypePrinter.h.
References ARM_COMPUTE_ERROR, arm_compute::cpu::data_layout, NCDHW, NCHW, NDHWC, NHWC, and UNKNOWN.
| inline ::std::ostream& arm_compute::operator<< | ( | ::std::ostream & | os, |
| const DataLayoutDimension & | data_layout_dim | ||
| ) |
[Print DataLayout type]
Formatted output of the DataLayoutDimension type.
| [out] | os | Output stream. |
| [in] | data_layout_dim | Data layout dimension to print. |
Definition at line 743 of file TypePrinter.h.
References ARM_COMPUTE_ERROR, BATCHES, CHANNEL, DEPTH, HEIGHT, and WIDTH.
| inline ::std::ostream& arm_compute::operator<< | ( | ::std::ostream & | os, |
| const DataType & | data_type | ||
| ) |
Formatted output of the DataType type.
| [out] | os | Output stream. |
| [in] | data_type | Type to output. |
Definition at line 775 of file TypePrinter.h.
References ARM_COMPUTE_ERROR, BFLOAT16, arm_compute::test::validation::data_type, F16, F32, F64, QASYMM16, QASYMM8, QASYMM8_SIGNED, QSYMM16, QSYMM8, QSYMM8_PER_CHANNEL, S16, S32, S64, S8, SIZET, U16, U32, U64, U8, and UNKNOWN.
| inline ::std::ostream& arm_compute::operator<< | ( | ::std::ostream & | os, |
| const DetectionOutputLayerCodeType & | detection_code | ||
| ) |
Formatted output of the DetectionOutputLayerCodeType type.
| [out] | os | Output stream |
| [in] | detection_code | Type to output |
Definition at line 2358 of file TypePrinter.h.
References ARM_COMPUTE_ERROR, CENTER_SIZE, CORNER, CORNER_SIZE, and TF_CENTER.
| inline ::std::ostream& arm_compute::operator<< | ( | ::std::ostream & | os, |
| const DetectionOutputLayerInfo & | detection_info | ||
| ) |
Formatted output of the DetectionOutputLayerInfo type.
| [out] | os | Output stream |
| [in] | detection_info | Type to output |
Definition at line 2400 of file TypePrinter.h.
References DetectionOutputLayerInfo::background_label_id(), DetectionOutputLayerInfo::code_type(), DetectionOutputLayerInfo::confidence_threshold(), DetectionOutputLayerInfo::eta(), DetectionOutputLayerInfo::keep_top_k(), DetectionOutputLayerInfo::nms_threshold(), DetectionOutputLayerInfo::num_classes(), DetectionOutputLayerInfo::num_loc_classes(), DetectionOutputLayerInfo::share_location(), DetectionOutputLayerInfo::top_k(), and DetectionOutputLayerInfo::variance_encoded_in_target().
| inline ::std::ostream& arm_compute::operator<< | ( | ::std::ostream & | os, |
| const DetectionPostProcessLayerInfo & | detection_info | ||
| ) |
Formatted output of the DetectionPostProcessLayerInfo type.
| [out] | os | Output stream |
| [in] | detection_info | Type to output |
Definition at line 2436 of file TypePrinter.h.
References DetectionPostProcessLayerInfo::detection_per_class(), DetectionPostProcessLayerInfo::iou_threshold(), DetectionPostProcessLayerInfo::max_classes_per_detection(), DetectionPostProcessLayerInfo::max_detections(), DetectionPostProcessLayerInfo::nms_score_threshold(), DetectionPostProcessLayerInfo::num_classes(), DetectionPostProcessLayerInfo::scale_value_h(), DetectionPostProcessLayerInfo::scale_value_w(), DetectionPostProcessLayerInfo::scale_value_x(), DetectionPostProcessLayerInfo::scale_value_y(), and DetectionPostProcessLayerInfo::use_regular_nms().
| inline ::std::ostream& arm_compute::operator<< | ( | ::std::ostream & | os, |
| const DetectionWindow & | detection_window | ||
| ) |
Formatted output of the DetectionWindow type.
| [out] | os | Output stream |
| [in] | detection_window | Type to output |
Definition at line 2339 of file TypePrinter.h.
References DetectionWindow::height, DetectionWindow::idx_class, DetectionWindow::score, DetectionWindow::width, DetectionWindow::x, and DetectionWindow::y.
| inline ::std::ostream& arm_compute::operator<< | ( | ::std::ostream & | os, |
| const DimensionRoundingType & | rounding_type | ||
| ) |
Formatted output of the DimensionRoundingType type.
| [out] | os | Output stream. |
| [in] | rounding_type | DimensionRoundingType Dimension rounding type when down-scaling, or compute output shape of pooling(2D or 3D). |
Definition at line 2063 of file TypePrinter.h.
References ARM_COMPUTE_ERROR, CEIL, and FLOOR.
| inline ::std::ostream& arm_compute::operator<< | ( | ::std::ostream & | os, |
| const Dimensions< T > & | dimensions | ||
| ) |
Formatted output of the Dimensions type.
| [out] | os | Output stream. |
| [in] | dimensions | Type to output. |
Definition at line 163 of file TypePrinter.h.
References Dimensions< T >::num_dimensions().
| inline ::std::ostream& arm_compute::operator<< | ( | ::std::ostream & | os, |
| const ElementWiseUnary & | op | ||
| ) |
Formatted output of the Elementwise unary Operations.
| [out] | os | Output stream. |
| [in] | op | Type to output. |
Definition at line 1893 of file TypePrinter.h.
References ABS, ARM_COMPUTE_ERROR, EXP, LOG, LOGICAL_NOT, NEG, ROUND, RSQRT, and SIN.
| inline ::std::ostream& arm_compute::operator<< | ( | ::std::ostream & | os, |
| const experimental::dynamic_fusion::CastAttributes & | cast_attr | ||
| ) |
Formatted output of the arm_compute::experimental::dynamic_fusion::CastAttributes type.
| [out] | os | Output stream. |
| [in] | cast_attr | arm_compute::experimental::dynamic_fusion::CastAttributes type to output. |
Definition at line 3389 of file TypePrinter.h.
References CastAttributes::convert_policy(), and CastAttributes::data_type().
| inline ::std::ostream& arm_compute::operator<< | ( | ::std::ostream & | os, |
| const experimental::dynamic_fusion::ClampAttributes & | clamp_attr | ||
| ) |
Formatted output of the arm_compute::experimental::dynamic_fusion::ClampAttributes type.
| [out] | os | Output stream. |
| [in] | clamp_attr | arm_compute::experimental::dynamic_fusion::ClampAttributes type to output. |
Definition at line 3451 of file TypePrinter.h.
References ClampAttributes::max_val(), and ClampAttributes::min_val().
| inline ::std::ostream& arm_compute::operator<< | ( | ::std::ostream & | os, |
| const experimental::dynamic_fusion::Conv2dAttributes & | conv2d_attr | ||
| ) |
Formatted output of the arm_compute::experimental::dynamic_fusion::Conv2dAttributes type.
| [out] | os | Output stream. |
| [in] | conv2d_attr | arm_compute::experimental::dynamic_fusion::Conv2dAttributes type to output. |
Definition at line 3358 of file TypePrinter.h.
References Conv2dAttributes::dilation(), Conv2dAttributes::pad(), and Conv2dAttributes::stride().
| inline ::std::ostream& arm_compute::operator<< | ( | ::std::ostream & | os, |
| const experimental::dynamic_fusion::DepthwiseConv2dAttributes & | dw_conv2d_attr | ||
| ) |
Formatted output of the arm_compute::experimental::dynamic_fusion::DepthwiseConv2dAttributes type.
| [out] | os | Output stream. |
| [in] | dw_conv2d_attr | arm_compute::experimental::dynamic_fusion::DepthwiseConv2dAttributes type to output. |
Definition at line 3418 of file TypePrinter.h.
References DepthwiseConv2dAttributes::depth_multiplier(), DepthwiseConv2dAttributes::dilation(), DepthwiseConv2dAttributes::dimension_rounding_type(), DepthwiseConv2dAttributes::pad(), and DepthwiseConv2dAttributes::stride().
| inline ::std::ostream& arm_compute::operator<< | ( | ::std::ostream & | os, |
| const experimental::dynamic_fusion::GpuPool2dSettings & | settings | ||
| ) |
Formatted output of the arm_compute::experimental::dynamic_fusion::GpuPool2dSettings type.
| [out] | os | Output stream |
| [in] | settings | arm_compute::dynamic_fusion::GpuPool2dSettings type to output |
Definition at line 3330 of file TypePrinter.h.
References GpuPool2dSettings::use_inf_as_limit().
| inline ::std::ostream& arm_compute::operator<< | ( | ::std::ostream & | os, |
| const experimental::dynamic_fusion::Pool2dAttributes & | pool2d_attr | ||
| ) |
Formatted output of the arm_compute::experimental::dynamic_fusion::Pool2dAttributes type.
| [out] | os | Output stream. |
| [in] | pool2d_attr | arm_compute::experimental::dynamic_fusion::Pool2dAttributes type to output. |
Definition at line 3299 of file TypePrinter.h.
References Pool2dAttributes::exclude_padding(), Pool2dAttributes::pad(), Pool2dAttributes::pool_size(), Pool2dAttributes::pool_type(), and Pool2dAttributes::stride().
| inline ::std::ostream& arm_compute::operator<< | ( | ::std::ostream & | os, |
| const experimental::dynamic_fusion::ResizeAttributes & | resize_attr | ||
| ) |
Formatted output of the arm_compute::experimental::dynamic_fusion::ResizeAttributes type.
| [out] | os | Output stream. |
| [in] | resize_attr | arm_compute::experimental::dynamic_fusion::ResizeAttributes type to output. |
Definition at line 3479 of file TypePrinter.h.
References ResizeAttributes::align_corners(), ResizeAttributes::interpolation_policy(), ResizeAttributes::output_height(), ResizeAttributes::output_width(), and ResizeAttributes::sampling_policy().
| inline ::std::ostream& arm_compute::operator<< | ( | ::std::ostream & | os, |
| const experimental::dynamic_fusion::SoftmaxAttributes & | softmax_attr | ||
| ) |
Formatted output of the arm_compute::experimental::dynamic_fusion::SoftmaxAttributes type.
| [out] | os | Output stream. |
| [in] | softmax_attr | arm_compute::experimental::dynamic_fusion::SoftmaxAttributes type to output. |
Definition at line 3511 of file TypePrinter.h.
References SoftmaxAttributes::axis(), SoftmaxAttributes::beta(), and SoftmaxAttributes::is_log_softmax().
| inline ::std::ostream& arm_compute::operator<< | ( | ::std::ostream & | os, |
| const FFT1DInfo & | fft1d_info | ||
| ) |
Formatted output of the FFT1DInfo type.
| [out] | os | Output stream. |
| [in] | fft1d_info | FFT1DInfo to output. |
Definition at line 2854 of file TypePrinter.h.
References FFT1DInfo::axis, and FFT1DInfo::direction.
| inline ::std::ostream& arm_compute::operator<< | ( | ::std::ostream & | os, |
| const FFT2DInfo & | fft2d_info | ||
| ) |
Formatted output of the FFT2DInfo type.
| [out] | os | Output stream. |
| [in] | fft2d_info | FFT2DInfo to output. |
Definition at line 2881 of file TypePrinter.h.
References FFT2DInfo::axis0, FFT2DInfo::axis1, and FFT2DInfo::direction.
| inline ::std::ostream& arm_compute::operator<< | ( | ::std::ostream & | os, |
| const FFTDirection & | fft_dir | ||
| ) |
Formatted output of the FFTDirection type.
| [out] | os | Output stream. |
| [in] | fft_dir | FFTDirection to output. |
Definition at line 2818 of file TypePrinter.h.
References ARM_COMPUTE_ERROR, Forward, and Inverse.
| inline ::std::ostream& arm_compute::operator<< | ( | ::std::ostream & | os, |
| const Format & | format | ||
| ) |
Formatted output of the Format type.
| [out] | os | Output stream. |
| [in] | format | Type to output. |
Definition at line 866 of file TypePrinter.h.
References ARM_COMPUTE_ERROR, F16, F32, update_supported_ops::format, IYUV, NV12, NV21, RGB888, RGBA8888, S16, S32, U16, U32, U8, UNKNOWN, UV88, UYVY422, YUV444, and YUYV422.
| inline ::std::ostream& arm_compute::operator<< | ( | ::std::ostream & | os, |
| const FullyConnectedLayerInfo & | layer_info | ||
| ) |
Formatted output of the FullyConnectedLayerInfo type.
| [out] | os | Output stream. |
| [in] | layer_info | FullyConnectedLayerInfo to output. |
Definition at line 2620 of file TypePrinter.h.
References FullyConnectedLayerInfo::activation_info, FullyConnectedLayerInfo::are_weights_reshaped, FullyConnectedLayerInfo::fp_mixed_precision, FullyConnectedLayerInfo::retain_internal_weights, to_string(), FullyConnectedLayerInfo::transpose_weights, and FullyConnectedLayerInfo::weights_trained_layout.
| inline ::std::ostream& arm_compute::operator<< | ( | ::std::ostream & | os, |
| const FuseBatchNormalizationType & | fuse_type | ||
| ) |
Formatted output of the FuseBatchNormalizationType type.
| [out] | os | Output stream. |
| [in] | fuse_type | FuseBatchNormalizationType to output. |
Definition at line 2936 of file TypePrinter.h.
References ARM_COMPUTE_ERROR, CONVOLUTION, and DEPTHWISECONVOLUTION.
| inline ::std::ostream& arm_compute::operator<< | ( | ::std::ostream & | os, |
| const GEMMInfo & | info | ||
| ) |
Formatted output of the GEMMInfo type.
| [out] | os | Output stream. |
| [in] | info | Type to output. |
Definition at line 1412 of file TypePrinter.h.
References arm_compute::test::validation::info.
| inline ::std::ostream& arm_compute::operator<< | ( | ::std::ostream & | os, |
| const GEMMKernelInfo & | gemm_info | ||
| ) |
Formatted output of the GEMMKernelInfo type.
| [out] | os | Output stream. |
| [in] | gemm_info | Type to output. |
Definition at line 254 of file TypePrinter.h.
References GEMMKernelInfo::a_offset, GEMMKernelInfo::b_offset, GEMMKernelInfo::broadcast_bias, GEMMKernelInfo::depth_output_gemm3d, GEMMKernelInfo::fp_mixed_precision, GEMMKernelInfo::k, GEMMKernelInfo::m, GEMMKernelInfo::mult_interleave4x4_height, GEMMKernelInfo::mult_transpose1xW_width, GEMMKernelInfo::n, and GEMMKernelInfo::reinterpret_input_as_3d.
| inline ::std::ostream& arm_compute::operator<< | ( | ::std::ostream & | os, |
| const GEMMLHSMatrixInfo & | gemm_info | ||
| ) |
Formatted output of the GEMMLHSMatrixInfo type.
| [out] | os | Output stream. |
| [in] | gemm_info | Type to output. |
Definition at line 278 of file TypePrinter.h.
References GEMMLHSMatrixInfo::interleave, GEMMLHSMatrixInfo::k0, GEMMLHSMatrixInfo::m0, GEMMLHSMatrixInfo::transpose, and GEMMLHSMatrixInfo::v0.
| inline ::std::ostream& arm_compute::operator<< | ( | ::std::ostream & | os, |
| const GEMMLowpOutputStageInfo & | gemm_info | ||
| ) |
Formatted output of the GEMMLowpOutputStageInfo type.
| [out] | os | Output stream. |
| [in] | gemm_info | GEMMLowpOutputStageInfo to output. |
Definition at line 2693 of file TypePrinter.h.
References GEMMLowpOutputStageInfo::gemmlowp_max_bound, GEMMLowpOutputStageInfo::gemmlowp_min_bound, GEMMLowpOutputStageInfo::gemmlowp_multiplier, GEMMLowpOutputStageInfo::gemmlowp_offset, GEMMLowpOutputStageInfo::gemmlowp_real_multiplier, GEMMLowpOutputStageInfo::gemmlowp_shift, GEMMLowpOutputStageInfo::is_quantized_per_channel, GEMMLowpOutputStageInfo::output_data_type, and GEMMLowpOutputStageInfo::type.
| inline ::std::ostream& arm_compute::operator<< | ( | ::std::ostream & | os, |
| const GEMMLowpOutputStageType & | gemm_type | ||
| ) |
Formatted output of the GEMMLowpOutputStageType type.
| [out] | os | Output stream. |
| [in] | gemm_type | GEMMLowpOutputStageType to output. |
Definition at line 2651 of file TypePrinter.h.
References ARM_COMPUTE_ERROR, arm_compute::mlgo::parser::gemm_type(), NONE, QUANTIZE_DOWN, QUANTIZE_DOWN_FIXEDPOINT, and QUANTIZE_DOWN_FLOAT.
| inline ::std::ostream& arm_compute::operator<< | ( | ::std::ostream & | os, |
| const GEMMReshapeInfo & | info | ||
| ) |
Formatted output of the GEMMReshapeInfo type.
| [out] | os | Output stream. |
| [in] | info | Type to output. |
Definition at line 1393 of file TypePrinter.h.
References arm_compute::test::validation::info.
| inline ::std::ostream& arm_compute::operator<< | ( | ::std::ostream & | os, |
| const GEMMRHSMatrixInfo & | gemm_info | ||
| ) |
Formatted output of the GEMMRHSMatrixInfo type.
| [out] | os | Output stream. |
| [in] | gemm_info | Type to output. |
Definition at line 292 of file TypePrinter.h.
References GEMMRHSMatrixInfo::export_to_cl_image, GEMMRHSMatrixInfo::h0, GEMMRHSMatrixInfo::interleave, GEMMRHSMatrixInfo::k0, GEMMRHSMatrixInfo::n0, and GEMMRHSMatrixInfo::transpose.
| inline ::std::ostream& arm_compute::operator<< | ( | ::std::ostream & | os, |
| const GenerateProposalsInfo & | proposals_info | ||
| ) |
Formatted output of the GenerateProposalsInfo type.
| [out] | os | Output stream. |
| [in] | proposals_info | Type to output. |
Definition at line 407 of file TypePrinter.h.
References GenerateProposalsInfo::im_height(), GenerateProposalsInfo::im_scale(), and GenerateProposalsInfo::im_width().
| inline ::std::ostream& arm_compute::operator<< | ( | ::std::ostream & | os, |
| const GPUTarget & | gpu_target | ||
| ) |
Formatted output of the GPUTarget type.
| [out] | os | Output stream |
| [in] | gpu_target | Type to output |
Definition at line 2215 of file TypePrinter.h.
References ARM_COMPUTE_ERROR, BIFROST, FIFTHGEN, G31, G310, G51, G510, G51BIG, G51LIT, G52, G52LIT, G57, G610, G615, G620, G68, G71, G710, G715, G72, G720, G76, G77, G78, G78AE, GPU_ARCH_MASK, GPU_GENERATION_MASK, MIDGARD, T600, T700, T800, and VALHALL.
| inline ::std::ostream& arm_compute::operator<< | ( | ::std::ostream & | os, |
| const InterpolationPolicy & | policy | ||
| ) |
Formatted output of the InterpolationPolicy type.
| [out] | os | Output stream. |
| [in] | policy | Type to output. |
Definition at line 1092 of file TypePrinter.h.
References AREA, ARM_COMPUTE_ERROR, BILINEAR, and NEAREST_NEIGHBOR.
| ::std::ostream& arm_compute::operator<< | ( | ::std::ostream & | os, |
| const LSTMParams< T > & | lstm_params | ||
| ) |
Formatted output of the ScaleKernelInfo type.
| [out] | os | Output stream. |
| [in] | lstm_params | LSTMParams to output. |
Definition at line 3002 of file TypePrinter.h.
References LSTMParams< T >::cell_clip(), LSTMParams< T >::cell_intermediate_scale(), LSTMParams< T >::cell_layer_norm_weights(), LSTMParams< T >::cell_to_forget_weights(), LSTMParams< T >::cell_to_input_weights(), LSTMParams< T >::cell_to_output_weights(), LSTMParams< T >::forget_intermediate_scale(), LSTMParams< T >::forget_layer_norm_weights(), LSTMParams< T >::has_cifg_opt(), LSTMParams< T >::has_peephole_opt(), LSTMParams< T >::has_projection(), LSTMParams< T >::hidden_state_scale(), LSTMParams< T >::hidden_state_zero(), LSTMParams< T >::input_gate_bias(), LSTMParams< T >::input_intermediate_scale(), LSTMParams< T >::input_layer_norm_weights(), LSTMParams< T >::input_to_input_weights(), LSTMParams< T >::output_layer_norm_weights(), LSTMParams< T >::projection_bias(), LSTMParams< T >::projection_clip(), LSTMParams< T >::projection_weights(), LSTMParams< T >::recurrent_to_input_weights(), to_string(), and LSTMParams< T >::use_layer_norm().
| inline ::std::ostream& arm_compute::operator<< | ( | ::std::ostream & | os, |
| const Multiples & | multiples | ||
| ) |
Formatted output of the Multiples type.
| [out] | os | Output stream. |
| [in] | multiples | Type to output. |
Definition at line 1074 of file TypePrinter.h.
| inline ::std::ostream& arm_compute::operator<< | ( | ::std::ostream & | os, |
| const NMSType & | nms_type | ||
| ) |
Available non maxima suppression types.
Formatted output of the NMSType type.
| [out] | os | Output stream. |
| [in] | nms_type | NMSType to output. |
Definition at line 3064 of file TypePrinter.h.
References ARM_COMPUTE_ERROR, GAUSSIAN, LINEAR, and ORIGINAL.
| inline ::std::ostream& arm_compute::operator<< | ( | ::std::ostream & | os, |
| const NormalizationLayerInfo & | info | ||
| ) |
Formatted output of NormalizationLayerInfo.
| [out] | os | Output stream. |
| [in] | info | Type to output. |
Definition at line 628 of file TypePrinter.h.
References arm_compute::test::validation::info.
| inline ::std::ostream& arm_compute::operator<< | ( | ::std::ostream & | os, |
| const NormType & | norm_type | ||
| ) |
Formatted output of the NormType type.
| [out] | os | Output stream. |
| [in] | norm_type | Type to output. |
Definition at line 588 of file TypePrinter.h.
References ARM_COMPUTE_ERROR, CROSS_MAP, IN_MAP_1D, and IN_MAP_2D.
| inline ::std::ostream& arm_compute::operator<< | ( | ::std::ostream & | os, |
| const Padding2D & | padding2d | ||
| ) |
Formatted output of the Padding2D type.
| [out] | os | Output stream. |
| [in] | padding2d | Padding info for 2D dimension shape. |
Definition at line 3273 of file TypePrinter.h.
References Padding2D::bottom, Padding2D::left, Padding2D::right, and Padding2D::top.
| inline ::std::ostream& arm_compute::operator<< | ( | ::std::ostream & | os, |
| const Padding3D & | padding3d | ||
| ) |
Formatted output of the Padding3D type.
| [out] | os | Output stream. |
| [in] | padding3d | Padding info for 3D spatial dimension shape. |
Definition at line 2036 of file TypePrinter.h.
References Padding3D::back, Padding3D::bottom, Padding3D::front, Padding3D::left, Padding3D::right, and Padding3D::top.
| inline ::std::ostream& arm_compute::operator<< | ( | ::std::ostream & | os, |
| const PaddingList & | padding | ||
| ) |
Formatted output of the PaddingList type.
| [out] | os | Output stream. |
| [in] | padding | Type to output. |
Definition at line 1056 of file TypePrinter.h.
| inline ::std::ostream& arm_compute::operator<< | ( | ::std::ostream & | os, |
| const PaddingMode & | mode | ||
| ) |
Formatted output of the PaddingMode type.
| [out] | os | Output stream. |
| [in] | mode | Type to output. |
Definition at line 1568 of file TypePrinter.h.
References ARM_COMPUTE_ERROR, CONSTANT, clang_tidy_rules::mode, REFLECT, and SYMMETRIC.
| inline ::std::ostream& arm_compute::operator<< | ( | ::std::ostream & | os, |
| const PadStrideInfo & | pad_stride_info | ||
| ) |
Formatted output of the PadStrideInfo type.
| [out] | os | Output stream. |
| [in] | pad_stride_info | Type to output. |
Definition at line 1608 of file TypePrinter.h.
References PadStrideInfo::pad_bottom(), PadStrideInfo::pad_left(), PadStrideInfo::pad_right(), PadStrideInfo::pad_top(), and PadStrideInfo::stride().
| inline ::std::ostream& arm_compute::operator<< | ( | ::std::ostream & | os, |
| const PixelValue & | pixel_value | ||
| ) |
Formatted output of the PixelValue type.
| [out] | os | Output stream. |
| [in] | pixel_value | PixelValue to output. |
Definition at line 2760 of file TypePrinter.h.
References PixelValue::get().
| inline ::std::ostream& arm_compute::operator<< | ( | ::std::ostream & | os, |
| const Pooling3dLayerInfo & | info | ||
| ) |
Formatted output of the Pooling 3d Layer Info.
| [out] | os | Output stream. |
| [in] | info | Pooling 3D layer info to print to output stream. |
Definition at line 2086 of file TypePrinter.h.
References arm_compute::test::validation::info.
| inline ::std::ostream& arm_compute::operator<< | ( | ::std::ostream & | os, |
| const PoolingLayerInfo & | info | ||
| ) |
Formatted output of PoolingLayerInfo.
| [out] | os | Output stream. |
| [in] | info | Type to output. |
Definition at line 668 of file TypePrinter.h.
References arm_compute::test::validation::info.
| inline ::std::ostream& arm_compute::operator<< | ( | ::std::ostream & | os, |
| const PoolingType & | pool_type | ||
| ) |
Formatted output of the PoolingType type.
| [out] | os | Output stream. |
| [in] | pool_type | Type to output. |
Definition at line 641 of file TypePrinter.h.
References ARM_COMPUTE_ERROR, AVG, L2, and MAX.
| inline ::std::ostream& arm_compute::operator<< | ( | ::std::ostream & | os, |
| const PriorBoxLayerInfo & | info | ||
| ) |
Formatted output of PriorBoxLayerInfo.
| [out] | os | Output stream. |
| [in] | info | Type to output. |
Definition at line 2486 of file TypePrinter.h.
References arm_compute::test::validation::info.
| inline ::std::ostream& arm_compute::operator<< | ( | ::std::ostream & | os, |
| const QuantizationInfo & | qinfo | ||
| ) |
Formatted output of the QuantizationInfo type.
| [out] | os | Output stream. |
| [in] | qinfo | Type to output. |
Definition at line 433 of file TypePrinter.h.
References UniformQuantizationInfo::offset, arm_compute::test::validation::qinfo, UniformQuantizationInfo::scale, and QuantizationInfo::uniform().
| inline ::std::ostream& arm_compute::operator<< | ( | ::std::ostream & | os, |
| const Rectangle & | rect | ||
| ) |
Formatted output of the Rectangle type.
| [out] | os | Output stream. |
| [in] | rect | Type to output. |
Definition at line 1553 of file TypePrinter.h.
References Rectangle::height, Rectangle::width, Rectangle::x, and Rectangle::y.
| inline ::std::ostream& arm_compute::operator<< | ( | ::std::ostream & | os, |
| const ReductionOperation & | op | ||
| ) |
Formatted output of the Reduction Operations.
| [out] | os | Output stream. |
| [in] | op | Type to output. |
Definition at line 1802 of file TypePrinter.h.
References ARG_IDX_MAX, ARG_IDX_MIN, ARM_COMPUTE_ERROR, MAX, MEAN_SUM, MIN, PROD, SUM, and SUM_SQUARE.
| inline ::std::ostream& arm_compute::operator<< | ( | ::std::ostream & | os, |
| const ROIPoolingLayerInfo & | pool_info | ||
| ) |
Formatted output of the ROIPoolingInfo type.
| [out] | os | Output stream. |
| [in] | pool_info | Type to output. |
Definition at line 228 of file TypePrinter.h.
References ROIPoolingLayerInfo::pooled_height(), ROIPoolingLayerInfo::pooled_width(), and ROIPoolingLayerInfo::spatial_scale().
| inline ::std::ostream& arm_compute::operator<< | ( | ::std::ostream & | os, |
| const RoundingPolicy & | rounding_policy | ||
| ) |
Formatted output of the RoundingPolicy type.
| [out] | os | Output stream. |
| [in] | rounding_policy | Type to output. |
Definition at line 185 of file TypePrinter.h.
References ARM_COMPUTE_ERROR, TO_NEAREST_EVEN, TO_NEAREST_UP, and TO_ZERO.
| inline ::std::ostream& arm_compute::operator<< | ( | ::std::ostream & | os, |
| const SamplingPolicy & | policy | ||
| ) |
Formatted output of the SamplingPolicy type.
| [out] | os | Output stream. |
| [in] | policy | Type to output. |
Definition at line 1119 of file TypePrinter.h.
References ARM_COMPUTE_ERROR, CENTER, and TOP_LEFT.
| inline ::std::ostream& arm_compute::operator<< | ( | ::std::ostream & | os, |
| const ScaleKernelInfo & | scale_info | ||
| ) |
Formatted output of the ScaleKernelInfo type.
| [out] | os | Output stream. |
| [in] | scale_info | ScaleKernelInfo to output. |
Definition at line 2786 of file TypePrinter.h.
References ScaleKernelInfo::align_corners, ScaleKernelInfo::border_mode, ScaleKernelInfo::constant_border_value, ScaleKernelInfo::data_layout, ScaleKernelInfo::interpolation_policy, ScaleKernelInfo::sampling_policy, and ScaleKernelInfo::use_padding.
| inline ::std::ostream& arm_compute::operator<< | ( | ::std::ostream & | os, |
| const ScatterFunction & | function | ||
| ) |
Formatted output of the scatter function type.
| [out] | os | Output stream. |
| [in] | function | arm_compute::ScatterFunction type to output. |
Definition at line 3629 of file TypePrinter.h.
References Add, ARM_COMPUTE_ERROR, Max, Min, Sub, and Update.
| inline ::std::ostream& arm_compute::operator<< | ( | ::std::ostream & | os, |
| const Size2D & | size | ||
| ) |
Formatted output of the Size2D type.
| [out] | os | Output stream |
| [in] | size | Type to output |
Definition at line 2142 of file TypePrinter.h.
References Size2D::height, and Size2D::width.
| inline ::std::ostream& arm_compute::operator<< | ( | ::std::ostream & | os, |
| const Size3D & | size | ||
| ) |
Formatted output of the Size3D type.
| [out] | os | Output stream |
| [in] | size | Type to output |
Definition at line 2009 of file TypePrinter.h.
References Size3D::depth, Size3D::height, and Size3D::width.
| inline ::std::ostream& arm_compute::operator<< | ( | ::std::ostream & | os, |
| const SoftmaxKernelInfo & | info | ||
| ) |
Formatted output of the SoftmaxKernelInfo type.
| [out] | os | Output stream. |
| [in] | info | SoftmaxKernelInfo to output. |
Definition at line 2972 of file TypePrinter.h.
References arm_compute::test::validation::info.
| ::std::ostream& arm_compute::operator<< | ( | ::std::ostream & | os, |
| const std::vector< T > & | args | ||
| ) |
Formatted output of a vector of objects.
| [out] | os | Output stream |
| [in] | args | Vector of objects to print |
Definition at line 110 of file TypePrinter.h.
References GemmTuner::args, to_string(), and arm_compute::utils::cast::U.
| inline ::std::ostream& arm_compute::operator<< | ( | ::std::ostream & | os, |
| const TensorInfo & | info | ||
| ) |
Formatted output of the const TensorInfo& type.
| [out] | os | Output stream. |
| [in] | info | Type to output. |
Definition at line 1173 of file TypePrinter.h.
References arm_compute::test::validation::info.
| inline ::std::ostream& arm_compute::operator<< | ( | ::std::ostream & | os, |
| const WeightsInfo & | weights_info | ||
| ) |
Formatted output of the WeightsInfo type.
| [out] | os | Output stream. |
| [in] | weights_info | Type to output. |
Definition at line 212 of file TypePrinter.h.
References arm_compute::test::validation::weights_info.
| inline ::std::ostream& arm_compute::operator<< | ( | ::std::ostream & | os, |
| const Window & | win | ||
| ) |
Formatted output of the Window type.
| [out] | os | Output stream. |
| [in] | win | Type to output. |
Definition at line 1448 of file TypePrinter.h.
References Dimensions< int >::num_max_dimensions.
| inline ::std::ostream& arm_compute::operator<< | ( | ::std::ostream & | os, |
| const Window::Dimension & | dim | ||
| ) |
Formatted output of the Window::Dimension type.
| [out] | os | Output stream. |
| [in] | dim | Type to output. |
Definition at line 1435 of file TypePrinter.h.
References Window::Dimension::end(), Window::Dimension::start(), and Window::Dimension::step().
| inline ::std::ostream& arm_compute::operator<< | ( | ::std::ostream & | os, |
| const WinogradInfo & | info | ||
| ) |
Formatted output of the WinogradInfo type.
Definition at line 2496 of file TypePrinter.h.
References arm_compute::test::validation::info.
| inline ::std::ostream& arm_compute::operator<< | ( | std::ostream & | os, |
| const ITensorInfo * | info | ||
| ) |
Formatted output of the ITensorInfo type.
| [out] | os | Output stream. |
| [in] | info | Tensor information. |
Definition at line 1143 of file TypePrinter.h.
References arm_compute::cpu::data_layout, ScaleKernelInfo::data_layout, arm_compute::test::validation::data_type, arm_compute::test::validation::info, is_data_type_quantized(), QuantizationInfo::offset(), arm_compute::test::validation::qinfo, QuantizationInfo::scale(), string_from_data_layout(), and string_from_data_type().
|
inline |
Check that given dimensions are equal.
| [in] | lhs | Left-hand side Dimensions. |
| [in] | rhs | Right-hand side Dimensions. |
Definition at line 275 of file Dimensions.h.
References Dimensions< T >::cbegin(), Dimensions< T >::cend(), and Dimensions< T >::num_dimensions().
Referenced by operator!=().
|
inline |
Check whether two quantization info are equal.
| [in] | lhs | RHS quantization info. |
| [in] | rhs | LHS quantization info. |
Definition at line 175 of file QuantizationInfo.h.
References QuantizationInfo::offset(), and QuantizationInfo::scale().
|
inline |
Check whether two tensor info are equal.
| [in] | lhs | LHS tensor info. |
| [in] | rhs | RHS tensor info. |
Definition at line 355 of file TensorInfo.h.
|
inline |
Check whether two quantization info are equal.
| [in] | lhs | RHS quantization info. |
| [in] | rhs | LHS quantization info. |
Definition at line 199 of file QuantizationInfo.h.
References UniformQuantizationInfo::offset, and UniformQuantizationInfo::scale.
|
inline |
| [in] | lhs | LHS valid region |
| [in] | rhs | RHS valid region |
Definition at line 225 of file Types.h.
References ValidRegion::anchor, and ValidRegion::shape.
| [in] | lhs | LHS window |
| [in] | rhs | RHS window |
Definition at line 323 of file Window.inl.
| inline ::std::istream& arm_compute::operator>> | ( | ::std::istream & | is, |
| BorderMode & | mode | ||
| ) |
Formatted input of the BorderMode type.
| [out] | is | Input stream. |
| [in] | mode | Border mode. |
Definition at line 42 of file TypeReader.h.
References CONSTANT, clang_tidy_rules::mode, REPLICATE, and UNDEFINED.
| inline ::std::istream& arm_compute::operator>> | ( | ::std::istream & | stream, |
| arm_compute::DataLayout & | data_layout | ||
| ) |
Input Stream operator for DataLayout.
| [in] | stream | Stream to parse |
| [out] | data_layout | Output data layout |
Definition at line 48 of file TypeLoader.h.
References arm_compute::cpu::data_layout, and data_layout_from_name().
| inline ::std::istream& arm_compute::operator>> | ( | ::std::istream & | stream, |
| CLTunerMode & | tuner_mode | ||
| ) |
Input Stream operator for CLTunerMode.
| [in] | stream | Stream to parse |
| [out] | tuner_mode | Output tuner mode |
Definition at line 87 of file CLTunerTypes.h.
References tuner_mode_from_name().
| inline ::std::istream& arm_compute::operator>> | ( | ::std::istream & | stream, |
| DataType & | data_type | ||
| ) |
Input Stream operator for DataType.
| [in] | stream | Stream to parse |
| [out] | data_type | Output data type |
Definition at line 290 of file DataTypeUtils.h.
References arm_compute::test::validation::data_type, and data_type_from_name().
|
inline |
Permutes given Dimensions according to a permutation vector.
| [in,out] | dimensions | Dimensions to permute |
| [in] | perm | Permutation vector |
Definition at line 144 of file Helpers.h.
References Dimensions< T >::begin(), Dimensions< T >::end(), Dimensions< T >::num_dimensions(), and Dimensions< T >::set().
Referenced by arm_compute::misc::shape_calculator::compute_permutation_output_shape(), PermuteLayerNode::configure_output(), NPYLoader::fill_tensor(), AssetsLibrary::fill_with_generator(), arm_compute::graph_utils::permute_shape(), arm_compute::test::validation::TEST_CASE(), CLDepthwiseConvolutionLayer::validate(), CLGEMMDeconvolutionLayer::validate(), arm_compute::test::validation::validate(), and arm_compute::test::validation::validate_wrap().
|
inline |
Permutes given TensorShape according to a permutation vector.
| [in,out] | shape | Shape to permute |
| [in] | perm | Permutation vector |
Definition at line 161 of file Helpers.h.
References Dimensions< T >::num_dimensions(), and arm_compute::test::validation::shape.
|
inline |
Permutes the given dimensions according the permutation vector.
| [in,out] | dimensions | Dimensions to be permuted. |
| [in] | perm | Vector describing the permutation. |
Definition at line 69 of file Utils.h.
References Dimensions< T >::begin(), Dimensions< T >::end(), Dimensions< T >::num_dimensions(), and Dimensions< T >::set().
|
inline |
The size in bytes of the pixel format.
| [in] | format | Input format |
Definition at line 38 of file FormatUtils.h.
References ARM_COMPUTE_ERROR, BFLOAT16, F16, F32, update_supported_ops::format, IYUV, NV12, NV21, RGB888, RGBA8888, S16, S32, U16, U32, U8, UV88, UYVY422, YUV444, and YUYV422.
Return the plane index of a given channel given an input format.
| [in] | format | Input format |
| [in] | channel | Input channel |
Definition at line 78 of file FormatUtils.h.
References ARM_COMPUTE_ERROR, BFLOAT16, F16, F32, update_supported_ops::format, IYUV, NV12, NV21, RGB888, RGBA8888, S16, S32, U, U16, U32, U8, UV88, UYVY422, V, Y, YUV444, and YUYV422.
| bool preferred_dummy_work_items_support | ( | const cl::Device & | device | ) |
Helper function to check if "dummy work-items" are preferred to have a power of two NDRange In case dummy work-items is enabled, it is OpenCL kernel responsibility to check if the work-item is out-of range or not.
| [in] | device | A CL device |
Definition at line 370 of file CLHelpers.cpp.
References ARM_COMPUTE_UNUSED.
Referenced by ClGemmLowpMatrixMultiplyNativeKernel::configure(), ClGemmMatrixMultiplyNativeKernel::configure(), ClGemmLowpMatrixMultiplyReshapedKernel::configure(), ClGemmLowpMatrixMultiplyReshapedOnlyRhsKernel::configure(), ClGemmMatrixMultiplyReshapedOnlyRhsKernel::configure(), and ClGemmMatrixMultiplyReshapedKernel::configure().
| size_t preferred_vector_width | ( | const cl::Device & | device, |
| DataType | dt | ||
| ) |
Helper function to get the preferred native vector width size for built-in scalar types that can be put into vectors.
| [in] | device | A CL device |
| [in] | dt | data type |
Definition at line 340 of file CLHelpers.cpp.
References dt, F16, F32, QASYMM16, QASYMM8, QASYMM8_SIGNED, QSYMM16, QSYMM8, QSYMM8_PER_CHANNEL, S16, S32, S64, S8, U16, U32, U64, and U8.
|
inline |
Quantize a value given a 16-bit asymmetric quantization scheme.
| [in] | value | Value to quantize |
| [in] | qinfo | Quantization information to use for quantizing |
Definition at line 549 of file QuantizationInfo.h.
References arm_compute::test::validation::qinfo, quantize_qasymm16(), and QuantizationInfo::uniform().
|
inline |
Quantize a value given a 16-bit asymmetric quantization scheme.
| [in] | value | Value to quantize |
| [in] | qinfo | Quantization information to use for quantizing |
| [in] | rounding_policy | (Optional) Rounding policy to use. Default: nearest up |
Definition at line 521 of file QuantizationInfo.h.
References QuantizationInfo::offset(), arm_compute::test::validation::qinfo, round(), and QuantizationInfo::scale().
Referenced by arm_compute::cpu::bounding_box_transform_qsymm16(), PixelValue::PixelValue(), arm_compute::test::validation::reference::quantization_layer(), and quantize_qasymm16().
|
inline |
Quantize a value given an unsigned 8-bit asymmetric quantization scheme.
| [in] | value | Value to quantize |
| [in] | qinfo | Quantization information to use for quantizing |
| [in] | rounding_policy | (Optional) Rounding policy to use. Default: nearest up |
Definition at line 309 of file QuantizationInfo.h.
References arm_compute::test::validation::qinfo, and Qasymm8QuantizationHelper< QUANTIZED_TYPE >::quantize().
Referenced by ClActivationKernel::configure(), arm_compute::test::validation::convert_to_asymmetric(), arm_compute::scale_helpers::delta_bilinear_c1_quantized(), arm_compute::test::validation::reference::depthconcatenate_layer(), arm_compute::cpu::elementwise_arithm_op_quantized_scalar(), arm_compute::cpu::elementwise_op< uint8_t >(), VerifyAccessor< D >::fill_tensor(), get_quantized_activation_min_max(), arm_compute::quantization::get_quantized_asymmetric_output_min_max(), arm_compute::test::validation::get_quantized_bounds(), arm_compute::cpu::neon_qasymm8_activation(), PixelValue::PixelValue(), arm_compute::test::validation::reference::quantization_layer(), quantize_values(), arm_compute::cpu::roi_align_1x1_qasymm8(), CpuConcatenateHeightKernel::run_op(), CpuConcatenateWidthKernel::run_op(), and arm_compute::cpu::sve2_qasymm8_activation().
|
inline |
Quantize a value given a signed 8-bit asymmetric quantization scheme.
| [in] | value | Value to quantize |
| [in] | qinfo | Quantization information to use for quantizing |
| [in] | rounding_policy | (Optional) Rounding policy to use. Default: nearest up |
Definition at line 323 of file QuantizationInfo.h.
References arm_compute::test::validation::qinfo, and Qasymm8QuantizationHelper< QUANTIZED_TYPE >::quantize().
Referenced by ClActivationKernel::configure(), arm_compute::scale_helpers::delta_bilinear_c1_quantized(), arm_compute::cpu::elementwise_arithm_op_quantized_signed_scalar(), arm_compute::cpu::elementwise_op< int8_t >(), get_quantized_activation_min_max(), arm_compute::quantization::get_quantized_asymmetric_output_min_max(), arm_compute::test::validation::get_quantized_qasymm8_signed_bounds(), arm_compute::cpu::neon_qasymm8_signed_activation(), PixelValue::PixelValue(), arm_compute::test::validation::reference::quantization_layer(), arm_compute::cpu::roi_align_1x1_qasymm8(), CpuConcatenateWidthKernel::run_op(), CpuConcatenateHeightKernel::run_op(), arm_compute::cpu::sve2_qasymm8_signed_activation(), NEQLSTMLayer::validate(), and CLQLSTMLayer::validate().
|
inline |
Quantize a value given a 16-bit symmetric quantization scheme.
| [in] | value | Value to quantize |
| [in] | qinfo | Quantization information to use for quantizing |
Definition at line 496 of file QuantizationInfo.h.
References arm_compute::test::validation::qinfo, quantize_qsymm16(), and QuantizationInfo::uniform().
|
inline |
Quantize a value given a 16-bit symmetric quantization scheme.
| [in] | value | Value to quantize |
| [in] | qinfo | Quantization information to use for quantizing |
| [in] | rounding_policy | (Optional) Rounding policy to use. Default: nearest up |
Definition at line 468 of file QuantizationInfo.h.
References arm_compute::test::validation::qinfo, round(), and QuantizationInfo::scale().
Referenced by arm_compute::cpu::add_qsymm16_neon(), arm_compute::cpu::compute_all_anchors_qasymm16(), ClActivationKernel::configure(), NEQLSTMLayer::configure(), CLQLSTMLayer::configure(), arm_compute::test::validation::convert_to_symmetric(), arm_compute::cpu::neon_qsymm16_activation(), PixelValue::PixelValue(), quantize_qsymm16(), arm_compute::cpu::sub_qsymm16_neon(), NEQLSTMLayer::validate(), and CLQLSTMLayer::validate().
|
inline |
Quantize a value given a 8-bit symmetric quantization scheme.
| [in] | value | Value to quantize |
| [in] | qinfo | Quantization information to use for quantizing |
Definition at line 337 of file QuantizationInfo.h.
References arm_compute::test::validation::qinfo, round(), UniformQuantizationInfo::scale, TO_NEAREST_UP, and QuantizationInfo::uniform().
Referenced by PixelValue::PixelValue().
|
inline |
Quantize a value given a 8-bit symmetric per channel quantization scheme.
| [in] | value | Value to quantize |
| [in] | qinfo | Quantization information to use for quantizing |
| [in] | channel_id | channel index into the scale vector of quantization info |
Definition at line 352 of file QuantizationInfo.h.
References arm_compute::test::validation::qinfo, round(), QuantizationInfo::scale(), and TO_NEAREST_UP.
Referenced by arm_compute::test::validation::get_symm_quantized_per_channel_bounds().
| std::string read_file | ( | const std::string & | filename, |
| bool | binary | ||
| ) |
Load an entire file in memory.
| [in] | filename | Name of the file to read. |
| [in] | binary | Is it a binary file ? |
Definition at line 40 of file Utils.cpp.
References ARM_COMPUTE_ERROR_VAR, arm_compute::mlgo::parser::end(), and clang_tidy_rules::mode.
Referenced by ClKernelLibrary::program().
| void arm_compute::release_prepare_tensors | ( | WorkspaceData< TensorType > & | workspace, |
| ITensorPack & | prep_pack | ||
| ) |
Definition at line 105 of file MemoryHelpers.h.
Referenced by CLWinogradConvolutionLayer::prepare().
| void arm_compute::release_temporaries | ( | const experimental::MemoryRequirements & | mem_reqs, |
| WorkspaceData< TensorType > & | workspace | ||
| ) |
Utility function to release tensors with lifetime marked as Prepare.
Definition at line 122 of file MemoryHelpers.h.
References tensor.
Referenced by CLGEMMLowpMatrixMultiplyCore::prepare(), CLGEMMConvolutionLayer::prepare(), and CLConvolutionLayer::prepare().
| void restore_program_cache_from_file | ( | const std::string & | filename = "cache.bin" | ) |
This function loads prebuilt opencl kernels from a file.
| [in] | filename | Name of the file to be used to load the kernels |
Definition at line 35 of file Utils.cpp.
References CLKernelLibrary::add_built_program(), CLScheduler::context(), arm_compute::test::validation::context, CLScheduler::default_init(), CLKernelLibrary::get(), CLScheduler::get(), and name.
| int round | ( | float | x, |
| RoundingPolicy | rounding_policy | ||
| ) |
Return a rounded value of x.
Rounding is done according to the rounding_policy.
| [in] | x | Float value to be rounded. |
| [in] | rounding_policy | Policy determining how rounding is done. |
Definition at line 36 of file Rounding.cpp.
References ARM_COMPUTE_ERROR, arm_compute::support::cpp11::round(), TO_NEAREST_EVEN, TO_NEAREST_UP, and TO_ZERO.
Referenced by quantize(), Qasymm8QuantizationHelper< QUANTIZED_TYPE >::quantize(), quantize_qasymm16(), quantize_qsymm16(), quantize_qsymm8(), quantize_qsymm8_per_channel(), roi_pooling_layer(), scale_nearest_neighbour_nchw(), arm_compute::scheduler_utils::split_2d(), arm_compute::cpu::sve2_qasymm8_activation(), and arm_compute::cpu::sve2_qasymm8_signed_activation().
|
inline |
Round to the nearest division by a power-of-two using exponent.
| [in] | x | Element to divide. |
| [in] | exponent | Integer value used to round to nearest division by a power-of-two |
Definition at line 441 of file NEMath.inl.
|
inline |
Round to the nearest division by a power-of-two using exponent.
| [in] | x | Vector of 4 elements |
| [in] | exponent | Integer value used to round to nearest division by a power-of-two |
Definition at line 433 of file NEMath.inl.
|
inline |
Round to the nearest division by a power-of-two using exponent.
| [in] | x | Vector of 4 elements |
| [in] | exponent | Vector of 4 elements with integer value used to round to nearest division by a power-of-two |
Definition at line 425 of file NEMath.inl.
Referenced by finalize_quantization(), finalize_quantization_int16(), finalize_quantization_symm(), and multiply_by_quantized_multiplier_2row().
| void arm_compute::run_reverse | ( | const Window & | window, |
| const ITensor * | input, | ||
| const ITensor * | axis, | ||
| ITensor * | output, | ||
| bool | use_inverted_axis | ||
| ) |
Definition at line 96 of file NEReverseKernel.cpp.
References ARM_COMPUTE_ERROR, ITensor::buffer(), ITensorInfo::dimension(), Window::DimX, Window::Dimension::end(), execute_window_loop(), ITensor::info(), arm_compute::test::validation::input, Iterator::ptr(), ITensor::ptr_to_element(), Window::set(), Window::Dimension::start(), arm_compute::wrapper::vcombine(), arm_compute::wrapper::vgethigh(), arm_compute::wrapper::vgetlow(), arm_compute::wrapper::vloadq(), arm_compute::wrapper::vrev64(), arm_compute::wrapper::vstore(), and Window::x().
| void save_program_cache_to_file | ( | const std::string & | filename = "cache.bin" | ) |
This function saves opencl kernels library to a file.
| [in] | filename | Name of the file to be used to save the library |
Definition at line 73 of file Utils.cpp.
References ARM_COMPUTE_ERROR, ARM_COMPUTE_ERROR_ON, CLKernelLibrary::get(), CLScheduler::get(), and kernel_name.
| std::tuple< int, int, int > scaled_3d_dimensions_signed | ( | int | width, |
| int | height, | ||
| int | depth, | ||
| int | kernel_width, | ||
| int | kernel_height, | ||
| int | kernel_depth, | ||
| const Pooling3dLayerInfo & | pool3d_info | ||
| ) |
Returns calculated width, height and depth of output scaled tensor depending on dimensions rounding mode.
| [in] | width | Width of input tensor |
| [in] | height | Height of input tensor |
| [in] | depth | Depth of input tensor |
| [in] | kernel_width | Kernel width. |
| [in] | kernel_height | Kernel height. |
| [in] | kernel_depth | Kernel depth. |
| [in] | pool3d_info | Pad and stride and round information for 3d pooling |
Definition at line 366 of file Utils.cpp.
References ARM_COMPUTE_ERROR, Padding3D::back, Padding3D::bottom, CEIL, FLOOR, Padding3D::front, Padding3D::left, Pooling3dLayerInfo::padding, Padding3D::right, Pooling3dLayerInfo::round_type, Pooling3dLayerInfo::stride, Padding3D::top, arm_compute::test::validation::w, Size3D::x(), Size3D::y(), and Size3D::z().
Referenced by arm_compute::misc::shape_calculator::compute_pool3d_shape().
| std::pair< unsigned int, unsigned int > scaled_dimensions | ( | int | width, |
| int | height, | ||
| int | kernel_width, | ||
| int | kernel_height, | ||
| const PadStrideInfo & | pad_stride_info, | ||
| const Size2D & | dilation = Size2D(1U, 1U) |
||
| ) |
Returns expected width and height of output scaled tensor depending on dimensions rounding mode.
| [in] | width | Width of input tensor (Number of columns) |
| [in] | height | Height of input tensor (Number of rows) |
| [in] | kernel_width | Kernel width. |
| [in] | kernel_height | Kernel height. |
| [in] | pad_stride_info | Pad and stride information. |
| [in] | dilation | (Optional) Dilation, in elements, across x and y. Defaults to (1, 1). |
Definition at line 288 of file Utils.cpp.
References ARM_COMPUTE_ERROR, CEIL, FLOOR, PadStrideInfo::pad_bottom(), PadStrideInfo::pad_left(), PadStrideInfo::pad_right(), PadStrideInfo::pad_top(), PadStrideInfo::round(), PadStrideInfo::stride(), arm_compute::test::validation::w, Size2D::x(), and Size2D::y().
Referenced by calculate_same_pad(), arm_compute::misc::shape_calculator::compute_deep_convolution_shape(), arm_compute::misc::shape_calculator::compute_depthwise_convolution_shape(), arm_compute::misc::shape_calculator::compute_im2col_conv_shape(), PoolingLayerNode::compute_output_descriptor(), FusedConvolutionBatchNormalizationNode::compute_output_descriptor(), FusedDepthwiseConvolutionBatchNormalizationNode::compute_output_descriptor(), DepthwiseConvolutionLayerNode::compute_output_descriptor(), ConvolutionLayerNode::compute_output_descriptor(), arm_compute::misc::shape_calculator::compute_winograd_output_transform_shape(), ClIm2ColKernel::configure(), CpuIm2ColKernel::configure(), CpuGemmConv2d::configure(), ClGemmConv2d::configure(), arm_compute::test::validation::reference::convolution_layer_nchw(), CpuGemmConv2d::has_opt_impl(), arm_compute::test::validation::reference::im2col_nchw(), arm_compute::test::validation::reference::im2col_nhwc(), ClGemmConv2d::validate(), and CpuGemmConv2d::validate().
| std::pair< int, int > scaled_dimensions_signed | ( | int | width, |
| int | height, | ||
| int | kernel_width, | ||
| int | kernel_height, | ||
| const PadStrideInfo & | pad_stride_info | ||
| ) |
Returns calculated width and height of output scaled tensor depending on dimensions rounding mode.
| [in] | width | Width of input tensor (Number of columns) |
| [in] | height | Height of input tensor (Number of rows) |
| [in] | kernel_width | Kernel width. |
| [in] | kernel_height | Kernel height. |
| [in] | pad_stride_info | Pad and stride information. |
Definition at line 334 of file Utils.cpp.
References ARM_COMPUTE_ERROR, CEIL, FLOOR, PadStrideInfo::pad_bottom(), PadStrideInfo::pad_left(), PadStrideInfo::pad_right(), PadStrideInfo::pad_top(), PadStrideInfo::round(), PadStrideInfo::stride(), and arm_compute::test::validation::w.
Referenced by arm_compute::misc::shape_calculator::compute_pool_shape().
| void schedule_kernel_on_ctx | ( | CLRuntimeContext * | ctx, |
| ICLKernel * | kernel, | ||
| bool | flush = true |
||
| ) |
Schedules a kernel using the context if not nullptr else uses the legacy scheduling flow.
| [in] | ctx | Context to use. |
| [in] | kernel | Kernel to schedule. |
| [in] | flush | (Optional) Specifies if the command queue will be flushed after running the kernel. |
Definition at line 138 of file CLHelpers.cpp.
References ARM_COMPUTE_ERROR_ON, ARM_COMPUTE_ERROR_ON_NULLPTR, CLScheduler::enqueue(), CLScheduler::get(), and CLRuntimeContext::gpu_scheduler().
Referenced by ICLSimpleFunction::run(), and CLInstanceNormalizationLayer::run().
| cl::Platform select_preferable_platform | ( | CLBackendType | cl_backend_type | ) |
This function selects the OpenCL platform based on the backend type.
| [in] | cl_backend_type | The OpenCL backend type to use. |
Definition at line 84 of file CLHelpers.cpp.
References ARM_COMPUTE_ERROR, ARM_COMPUTE_ERROR_ON_MSG, Clvk, and Native.
Referenced by create_opencl_context_and_device().
|
inline |
Set the data layout to the specified value if the current data layout is unknown.
| [in,out] | info | Tensor info used to check and assign. |
| [in] | data_layout | New data layout. |
Definition at line 152 of file AutoConfiguration.h.
References arm_compute::cpu::data_layout, ScaleKernelInfo::data_layout, arm_compute::test::validation::info, and UNKNOWN.
|
inline |
Set the data type and number of channels to the specified value if the current data type is unknown.
| [in,out] | info | Tensor info used to check and assign. |
| [in] | data_type | New data type. |
Definition at line 133 of file AutoConfiguration.h.
References arm_compute::test::validation::data_type, arm_compute::test::validation::info, and UNKNOWN.
Referenced by NELogicalKernel::configure(), CpuSubKernel::configure(), CpuAddMulAddKernel::configure(), and CpuAddKernel::configure().
|
inline |
Set the format, data type and number of channels to the specified value if the current data type is unknown.
| [in,out] | info | Tensor info used to check and assign. |
| [in] | format | New format. |
Definition at line 114 of file AutoConfiguration.h.
References update_supported_ops::format, arm_compute::test::validation::info, and UNKNOWN.
Referenced by NEBitwiseNotKernel::configure(), NEBitwiseXorKernel::configure(), NEBitwiseOrKernel::configure(), and NEBitwiseAndKernel::configure().
|
inline |
Set the quantization info to the specified value if the current quantization info is empty and the data type of asymmetric quantized type.
| [in,out] | info | Tensor info used to check and assign. |
| [in] | quantization_info | Quantization info |
Definition at line 171 of file AutoConfiguration.h.
References arm_compute::test::validation::info, and is_data_type_quantized_asymmetric().
|
inline |
Set the shape to the specified value if the current assignment is empty.
| [in,out] | info | Tensor info used to check and assign. |
| [in] | shape | New shape. |
Definition at line 95 of file AutoConfiguration.h.
References arm_compute::test::validation::info, and arm_compute::test::validation::shape.
Referenced by NELogicalKernel::configure(), NEBitwiseNotKernel::configure(), NEBitwiseXorKernel::configure(), NEBitwiseAndKernel::configure(), NEBitwiseOrKernel::configure(), CpuSubKernel::configure(), ClCastKernel::configure(), CpuAddMulAddKernel::configure(), CpuCastKernel::configure(), CpuAddKernel::configure(), and CpuMulKernel::configure().
| void set_unroll_with_pragma | ( | CLBuildOptions & | built_opts, |
| std::initializer_list< int > | values | ||
| ) |
Definition at line 487 of file CLHelpers.cpp.
References CLBuildOptions::add_option().
Referenced by CLDepthwiseConvolutionLayerNativeKernel::configure().
| void set_wbsm | ( | cl::Kernel & | kernel, |
| cl_int | wbsm_hint | ||
| ) |
Definition at line 441 of file CLHelpers.cpp.
References ARM_COMPUTE_ERROR_ON, ARM_COMPUTE_UNUSED, and clSetKernelExecInfo().
Referenced by enqueue().
| const std::string & string_from_activation_func | ( | const ActivationFunction & | act | ) |
Translates a given activation function to a string.
| [in] | act | ActivationLayerInfo::ActivationFunction to be translated to string. |
Definition at line 31 of file ActivationFunctionUtils.cpp.
References ABS, BOUNDED_RELU, ELU, GELU, HARD_SWISH, IDENTITY, LEAKY_RELU, LINEAR, LOGISTIC, LU_BOUNDED_RELU, RELU, SOFT_RELU, SQRT, SQUARE, SWISH, and TANH.
Referenced by ClActivationKernel::configure(), ClMatMulNativeKernel::configure(), ClMatMulLowpNativeKernel::configure(), ClGemmMatrixMultiplyNativeKernel::configure(), ClGemmMatrixMultiplyReshapedOnlyRhsMMULKernel::configure(), ClIndirectConv2dKernel::configure(), ClWinogradOutputTransformKernel::configure(), ClDirectConv2dKernel::configure(), ClMulKernel::configure(), ClGemmMatrixMultiplyReshapedOnlyRhsKernel::configure(), CLDepthwiseConvolutionLayerNativeKernel::configure(), ClGemmMatrixMultiplyReshapedKernel::configure(), CLBatchNormalizationLayerKernel::configure(), and ClComplexMulKernel::configure().
| const std::string & string_from_border_mode | ( | BorderMode | border_mode | ) |
Translates a given border mode policy to a string.
| [in] | border_mode | BorderMode to be translated to string. |
Definition at line 96 of file Utils.cpp.
References CONSTANT, REPLICATE, and UNDEFINED.
Referenced by CLFillBorderKernel::configure().
| const std::string & string_from_channel | ( | Channel | channel | ) |
| const std::string & string_from_data_layout | ( | DataLayout | dl | ) |
Convert a data layout identity into a string.
| [in] | dl | DataLayout to be translated to string. |
Definition at line 30 of file DataLayoutUtils.cpp.
References dl, NCHW, NHWC, and UNKNOWN.
Referenced by ClPool2dKernel::configure(), ClPool3dKernel::configure(), ClScaleKernel::configure(), CLChannelShuffleLayerKernel::configure(), ClWinogradFilterTransformKernel::configure(), ClWinogradInputTransformKernel::configure(), ClWinogradOutputTransformKernel::configure(), CLNormalizationLayerKernel::configure(), CLDepthToSpaceLayerKernel::configure(), CLSpaceToDepthLayerKernel::configure(), CLSpaceToBatchLayerKernel::configure(), CLComparisonKernel::configure(), CLReorgLayerKernel::configure(), CLBatchToSpaceLayerKernel::configure(), CLNormalizePlanarYUVLayerKernel::configure(), CpuScaleKernel::configure(), ClDirectConv2dKernel::configure(), ClIm2ColKernel::configure(), CLDeconvolutionReshapeOutputKernel::configure(), CLBatchNormalizationLayerKernel::configure(), error_on_data_layout_not_in(), and operator<<().
| const std::string & string_from_data_type | ( | DataType | dt | ) |
Convert a data type identity into a string.
| [in] | dt | DataType to be translated to string. |
Definition at line 31 of file DataTypeUtils.cpp.
References dt, F16, F32, F64, QASYMM16, QASYMM8, QASYMM8_SIGNED, QSYMM16, QSYMM8, QSYMM8_PER_CHANNEL, S16, S32, S64, S8, SIZET, U16, U32, U64, U8, and UNKNOWN.
Referenced by ClTransposedConvolutionKernel::configure(), CpuQuantizeKernel::configure(), ClMatMulLowpNativeMMULKernel::configure(), ClWidthConcatenate2TensorsKernel::configure(), ClPool2dKernel::configure(), ClPool3dKernel::configure(), ClActivationKernel::configure(), ClWidthConcatenate4TensorsKernel::configure(), ClMatMulNativeKernel::configure(), CLStridedSliceKernel::configure(), ClMatMulLowpNativeKernel::configure(), ClGemmReshapeLhsMatrixKernel::configure(), CLMaxUnpoolingLayerKernel::configure(), ClGemmMatrixMultiplyNativeKernel::configure(), ClGemmMatrixMultiplyReshapedOnlyRhsMMULKernel::configure(), CLChannelShuffleLayerKernel::configure(), ClIndirectConv2dKernel::configure(), CLSelectKernel::configure(), ClWinogradOutputTransformKernel::configure(), CLQLSTMLayerNormalizationKernel::configure(), CLFFTScaleKernel::configure(), ClSoftmaxKernel::configure(), CLNormalizationLayerKernel::configure(), CLTileKernel::configure(), CLComparisonKernel::configure(), ClCastKernel::configure(), CLFFTDigitReverseKernel::configure(), CLReorgLayerKernel::configure(), CLMeanStdDevNormalizationKernel::configure(), CLNormalizePlanarYUVLayerKernel::configure(), CLRangeKernel::configure(), CLReverseKernel::configure(), CpuScaleKernel::configure(), CLFFTRadixStageKernel::configure(), ClDirectConv2dKernel::configure(), ClCol2ImKernel::configure(), ClDirectConv3dKernel::configure(), ClMatMulNativeMMULKernel::configure(), ClMulKernel::configure(), ClGemmMatrixMultiplyReshapedOnlyRhsKernel::configure(), CLDepthwiseConvolutionLayerNativeKernel::configure(), ClIm2ColKernel::configure(), CLFillBorderKernel::configure(), ClGemmMatrixMultiplyReshapedKernel::configure(), CLDeconvolutionReshapeOutputKernel::configure(), CLBatchNormalizationLayerKernel::configure(), error_on_data_type_not_in(), GpuCkwElementwiseBinary::get_name(), and operator<<().
| const std::string & string_from_format | ( | Format | format | ) |
Convert a tensor format into a string.
| [in] | format | Format to be translated to string. |
Definition at line 31 of file FormatUtils.cpp.
References F16, F32, update_supported_ops::format, IYUV, NV12, NV21, RGB888, RGBA8888, S16, S32, U16, U32, U8, UNKNOWN, UV88, UYVY422, YUV444, and YUYV422.
Referenced by error_on_format_not_in().
| const std::string & string_from_gemmlowp_output_stage | ( | GEMMLowpOutputStageType | output_stage | ) |
Translates a given GEMMLowp output stage to a string.
| [in] | output_stage | GEMMLowpOutputStageInfo to be translated to string. |
Definition at line 154 of file Utils.cpp.
References NONE, output_stage, QUANTIZE_DOWN, QUANTIZE_DOWN_FIXEDPOINT, and QUANTIZE_DOWN_FLOAT.
Referenced by ClGemmLowpOffsetContributionOutputStageKernel::configure().
| const std::string & string_from_interpolation_policy | ( | InterpolationPolicy | policy | ) |
Translates a given interpolation policy to a string.
| [in] | policy | InterpolationPolicy to be translated to string. |
Definition at line 30 of file InterpolationPolicyUtils.cpp.
References AREA, BILINEAR, and NEAREST_NEIGHBOR.
Referenced by ClScaleKernel::configure(), and CpuScaleKernel::configure().
| const std::string & string_from_norm_type | ( | NormType | type | ) |
| std::string string_from_pixel_value | ( | const PixelValue & | value, |
| const DataType | data_type | ||
| ) |
Convert a PixelValue to a string, represented through the specific data type.
| [in] | value | The PixelValue to convert |
| [in] | data_type | The type to be used to convert the value |
Definition at line 165 of file Utils.cpp.
References ARM_COMPUTE_ERROR, arm_compute::test::validation::data_type, F16, F32, float_to_string_with_full_precision(), PixelValue::get(), QASYMM16, QASYMM8, QASYMM8_SIGNED, QSYMM16, QSYMM8_PER_CHANNEL, S16, S32, S8, arm_compute::test::validation::ss(), U16, U32, and U8.
Referenced by ClFillKernel::configure(), ClScaleKernel::configure(), and CLPadLayerKernel::configure().
| const std::string & string_from_pooling_type | ( | PoolingType | type | ) |
Translates a given pooling type to a string.
| [in] | type | PoolingType to be translated to string. |
Definition at line 118 of file Utils.cpp.
References AVG, L2, MAX, and type.
Referenced by ClPool2dKernel::configure(), and ClPool3dKernel::configure().
| const std::string & string_from_target | ( | GPUTarget | target | ) |
Translates a given gpu device target to string.
| [in] | target | Given gpu target. |
Definition at line 169 of file GPUTarget.cpp.
References BIFROST, FIFTHGEN, G31, G310, G51, G510, G51BIG, G51LIT, G52, G52LIT, G57, G610, G615, G620, G68, G71, G710, G715, G72, G720, G76, G77, G78, G78AE, MIDGARD, T600, T700, T800, and VALHALL.
Referenced by arm_compute::cl_gemm::auto_heuristics::select_mlgo_gemm_config_native(), arm_compute::cl_gemm::auto_heuristics::select_mlgo_gemm_config_reshaped(), arm_compute::cl_gemm::auto_heuristics::select_mlgo_gemm_config_reshaped_only_rhs(), and arm_compute::cl_gemm::auto_heuristics::select_mlgo_gemm_kernel().
| [in] | lhs | First window to swap. |
| [in] | rhs | Second window to swap. |
Definition at line 318 of file Window.inl.
Referenced by CaffePreproccessor::CaffePreproccessor().
| void throw_error | ( | Status | err | ) |
Throw an std::runtime_error.
| [in] | err | Error status |
Definition at line 47 of file Error.cpp.
References ARM_COMPUTE_THROW, and Status::error_description().
|
inline |
Converts a CLGEMMKernelType to string.
| [in] | val | CLGEMMKernelType value to be converted |
Definition at line 2548 of file TypePrinter.h.
References NATIVE, RESHAPED, and RESHAPED_ONLY_RHS.
|
inline |
Formatted output of the Arithmetic Operation.
| [in] | op | Type to output. |
Definition at line 1788 of file TypePrinter.h.
References caffe_mnist_image_extractor::str.
|
inline |
Formatted output of the activation function info type.
| [in] | info | ActivationLayerInfo to output. |
Definition at line 527 of file TypePrinter.h.
References arm_compute::test::validation::info, and caffe_mnist_image_extractor::str.
|
inline |
Formatted output of the activation function type.
| [in] | function | Type to output. |
Definition at line 574 of file TypePrinter.h.
References caffe_mnist_image_extractor::str.
|
inline |
Formatted output of the arm_compute::CpuMatMulSettings type.
| [in] | settings | arm_compute::CpuMatMulSettings type to output. |
Definition at line 3615 of file TypePrinter.h.
References caffe_mnist_image_extractor::str.
|
inline |
Formatted output of the DataLayout type.
| [in] | data_layout | Type to output. |
Definition at line 728 of file TypePrinter.h.
References arm_compute::cpu::data_layout, and caffe_mnist_image_extractor::str.
|
inline |
Formatted output of the DataType type.
| [in] | data_type | Type to output. |
Definition at line 852 of file TypePrinter.h.
References arm_compute::test::validation::data_type, and caffe_mnist_image_extractor::str.
|
inline |
Formatted output of the arm_compute::MatMulInfo type.
| [in] | matmul_info | arm_compute::MatMulInfo type to output. |
Definition at line 3554 of file TypePrinter.h.
References caffe_mnist_image_extractor::str.
|
inline |
Formatted output of the arm_compute::MatMulKernelInfo type.
| [in] | matmul_info | arm_compute::MatMulKernelInfo type to output. |
Definition at line 3587 of file TypePrinter.h.
References caffe_mnist_image_extractor::str.
|
inline |
Formatted output of NormalizationLayerInfo.
| [in] | info | Type to output. |
Definition at line 614 of file TypePrinter.h.
References arm_compute::test::validation::info, and caffe_mnist_image_extractor::str.
|
inline |
Formatted output of the arm_compute::ScatterFunction type.
| [in] | func | arm_compute::ScatterFunction type to output. |
Definition at line 3659 of file TypePrinter.h.
References caffe_mnist_image_extractor::str.
|
inline |
Formatted output of the arm_compute::ScatterInfo type.
| [in] | info | arm_compute::ScatterInfo type to output. |
Definition at line 3686 of file TypePrinter.h.
References arm_compute::test::validation::info, and caffe_mnist_image_extractor::str.
Referenced by to_string().
|
inline |
Formatted output of the BorderMode type.
| [in] | mode | Type to output. |
Definition at line 1637 of file TypePrinter.h.
References clang_tidy_rules::mode, and caffe_mnist_image_extractor::str.
|
inline |
Formatted output of the BorderSize type.
| [in] | border | Type to output. |
Definition at line 1650 of file TypePrinter.h.
References caffe_mnist_image_extractor::str.
|
inline |
Formatted output of the BoundingBoxTransformInfo type.
| [in] | bbox_info | Type to output. |
Definition at line 367 of file TypePrinter.h.
References caffe_mnist_image_extractor::str.
|
inline |
Converts a BoxNMSLimitInfo to string.
| [in] | info | BoxNMSLimitInfo value to be converted |
Definition at line 3123 of file TypePrinter.h.
References arm_compute::test::validation::info, and caffe_mnist_image_extractor::str.
|
inline |
Formatted output of the Channel type.
| [in] | channel | Type to output. |
Definition at line 1001 of file TypePrinter.h.
References caffe_mnist_image_extractor::str.
|
inline |
Formatted output of the arm_compute::experimental::dynamic_fusion::ClComponentElementwiseBinary::Attributes::ElementwiseOp type.
| [in] | op | arm_compute::experimental::dynamic_fusion::ClComponentElementwiseBinary::Attributes::ElementwiseOp type to output. |
Definition at line 68 of file ElementwiseBinary.h.
References caffe_mnist_image_extractor::str.
Referenced by ClSoftmaxKernel::configure(), arm_compute::graph::backends::detail::create_batch_normalization_layer(), arm_compute::graph::backends::detail::create_convolution_layer(), arm_compute::graph::backends::detail::create_depthwise_convolution_layer(), arm_compute::graph::backends::detail::create_fused_convolution_batch_normalization_layer(), arm_compute::graph::backends::detail::create_fused_depthwise_convolution_batch_normalization_layer(), InitializerListDataset< T >::iterator::description(), GpuCkwElementwiseBinary::get_name(), handle_cl_error(), arm_compute::test::framework::make_printable(), operator<<(), arm_compute::cl_gemm::auto_heuristics::select_mlgo_gemm_config_native(), arm_compute::cl_gemm::auto_heuristics::select_mlgo_gemm_config_reshaped(), arm_compute::cl_gemm::auto_heuristics::select_mlgo_gemm_config_reshaped_only_rhs(), arm_compute::cl_gemm::auto_heuristics::select_mlgo_gemm_kernel(), to_string(), to_string_if_not_null(), CpuGemm::validate(), DotGraphVisitor::visit(), and CLMutableCommandBuffer::~CLMutableCommandBuffer().
|
inline |
Convert a CLTunerMode value to a string.
| val | CLTunerMode value to be converted |
Definition at line 2519 of file TypePrinter.h.
References ARM_COMPUTE_ERROR, EXHAUSTIVE, NORMAL, and RAPID.
|
inline |
Formatted output of the Comparison Operations.
| [in] | op | Type to output. |
Definition at line 1934 of file TypePrinter.h.
References caffe_mnist_image_extractor::str.
|
inline |
Formatted output of the ComputeAnchorsInfo type.
| [in] | anchors_info | Type to output. |
Definition at line 393 of file TypePrinter.h.
References caffe_mnist_image_extractor::str.
|
inline |
Converts a Conv2dInfo to string.
| [in] | conv_info | Conv2dInfo value to be converted |
Definition at line 2746 of file TypePrinter.h.
References arm_compute::test::validation::conv_info, and caffe_mnist_image_extractor::str.
|
inline |
Formatted output of the Conv3dInfo type.
| [in] | conv3d_info | Type to output. |
Definition at line 3173 of file TypePrinter.h.
References caffe_mnist_image_extractor::str.
|
inline |
Definition at line 1733 of file TypePrinter.h.
References caffe_mnist_image_extractor::str.
|
inline |
Converts a ConvolutionInfo to string.
| [in] | info | ConvolutionInfo value to be converted |
Definition at line 2606 of file TypePrinter.h.
References arm_compute::test::validation::info, and caffe_mnist_image_extractor::str.
|
inline |
Formatted output of the ConvolutionMethod type.
| [in] | conv_method | Type to output |
Definition at line 2201 of file TypePrinter.h.
References caffe_mnist_image_extractor::str.
|
inline |
Formatted output of the Coordinates type.
| [in] | coord | Type to output. |
Definition at line 1379 of file TypePrinter.h.
References caffe_mnist_image_extractor::str.
|
inline |
Converts a Coordinates2D to string.
| [in] | coord_2d | Coordinates2D value to be converted |
Definition at line 2922 of file TypePrinter.h.
References caffe_mnist_image_extractor::str.
|
inline |
Formatted output of the DetectionOutputLayerCodeType type.
| [in] | detection_code | Type to output |
Definition at line 2386 of file TypePrinter.h.
References caffe_mnist_image_extractor::str.
|
inline |
Formatted output of the DetectionOutputLayerInfo type.
| [in] | detection_info | Type to output |
Definition at line 2423 of file TypePrinter.h.
References caffe_mnist_image_extractor::str.
|
inline |
Formatted output of the DetectionPostProcessLayerInfo type.
| [in] | detection_info | Type to output |
Definition at line 2459 of file TypePrinter.h.
References caffe_mnist_image_extractor::str.
|
inline |
Formatted output of the DetectionWindow type.
| [in] | detection_window | Type to output |
Definition at line 2472 of file TypePrinter.h.
References caffe_mnist_image_extractor::str.
|
inline |
Converts a DimensionRoundingType to string.
| [in] | rounding_type | DimensionRoundingType value to be converted |
Definition at line 3136 of file TypePrinter.h.
References caffe_mnist_image_extractor::str.
|
inline |
Formatted output of the Dimensions type.
| [in] | dimensions | Type to output. |
Definition at line 1340 of file TypePrinter.h.
References caffe_mnist_image_extractor::str.
|
inline |
Formatted output of the Elementwise unary Operations.
| [in] | op | Type to output. |
Definition at line 1947 of file TypePrinter.h.
References caffe_mnist_image_extractor::str.
|
inline |
Formatted output of the arm_compute::experimental::dynamic_fusion::CastAttributes type.
| [in] | cast_attr | arm_compute::experimental::dynamic_fusion::CastAttributes type to output. |
Definition at line 3404 of file TypePrinter.h.
References caffe_mnist_image_extractor::str.
|
inline |
Formatted output of the arm_compute::experimental::dynamic_fusion::ClampAttributes type.
| [in] | clamp_attr | arm_compute::experimental::dynamic_fusion::ClampAttributes type to output. |
Definition at line 3465 of file TypePrinter.h.
References caffe_mnist_image_extractor::str.
|
inline |
Formatted output of the arm_compute::experimental::dynamic_fusion::Conv2dAttributes type.
| [in] | conv2d_attr | arm_compute::experimental::dynamic_fusion::Conv2dAttributes type to output. |
Definition at line 3375 of file TypePrinter.h.
References caffe_mnist_image_extractor::str.
|
inline |
Formatted output of the arm_compute::experimental::dynamic_fusion::DepthwiseConv2dAttributes type.
| [in] | dw_conv2d_attr | arm_compute::experimental::dynamic_fusion::DepthwiseConv2dAttributes type to output. |
Definition at line 3437 of file TypePrinter.h.
References caffe_mnist_image_extractor::str.
|
inline |
Formatted output of the arm_compute::experimental::dynamic_fusion::GpuPool2dSettings type.
| [in] | settings | arm_compute::experimental::dynamic_fusion::GpuPool2dSettings type to output. |
Definition at line 3344 of file TypePrinter.h.
References caffe_mnist_image_extractor::str.
|
inline |
Formatted output of the arm_compute::experimental::dynamic_fusion::Pool2dAttributes type.
| [in] | pool2d_attr | arm_compute::experimental::dynamic_fusion::Pool2dAttributes type to output. |
Definition at line 3318 of file TypePrinter.h.
References caffe_mnist_image_extractor::str.
|
inline |
Formatted output of the arm_compute::experimental::dynamic_fusion::ResizeAttributes type.
| [in] | resize_attr | arm_compute::experimental::dynamic_fusion::ResizeAttributes type to output. |
Definition at line 3497 of file TypePrinter.h.
References caffe_mnist_image_extractor::str.
|
inline |
Formatted output of the arm_compute::experimental::dynamic_fusion::SoftmaxAttributes type.
| [in] | softmax_attr | arm_compute::experimental::dynamic_fusion::SoftmaxAttributes type to output. |
Definition at line 3527 of file TypePrinter.h.
References caffe_mnist_image_extractor::str.
|
inline |
Converts a FFT1DInfo to string.
| [in] | fft1d_info | FFT1DInfo value to be converted |
Definition at line 2867 of file TypePrinter.h.
References caffe_mnist_image_extractor::str.
|
inline |
Converts a FFT2DInfo to string.
| [in] | fft2d_info | FFT2DInfo value to be converted |
Definition at line 2895 of file TypePrinter.h.
References caffe_mnist_image_extractor::str.
|
inline |
Converts a FFT1DInfo to string.
| [in] | fft_dir | FFT1DInfo value to be converted |
Definition at line 2840 of file TypePrinter.h.
References caffe_mnist_image_extractor::str.
|
inline |
Formatted output of the Format type.
| [in] | format | Type to output. |
Definition at line 934 of file TypePrinter.h.
References update_supported_ops::format, and caffe_mnist_image_extractor::str.
|
inline |
Converts a FullyConnectedLayerInfo to string.
| [in] | info | FullyConnectedLayerInfo value to be converted |
Definition at line 2637 of file TypePrinter.h.
References arm_compute::test::validation::info, and caffe_mnist_image_extractor::str.
|
inline |
Converts a FuseBatchNormalizationType to string.
| [in] | fuse_type | FuseBatchNormalizationType value to be converted |
Definition at line 2958 of file TypePrinter.h.
References caffe_mnist_image_extractor::str.
|
inline |
Formatted output of the GEMMInfo type.
| [in] | info | Type to output. |
Definition at line 1496 of file TypePrinter.h.
References arm_compute::test::validation::info, and caffe_mnist_image_extractor::str.
|
inline |
Formatted output of the GEMMKernelInfo type.
| [in] | gemm_info | GEMMKernelInfo Type to output. |
Definition at line 332 of file TypePrinter.h.
References caffe_mnist_image_extractor::str.
|
inline |
Formatted output of the GEMMLHSMatrixInfo type.
| [in] | gemm_info | GEMMLHSMatrixInfo to output. |
Definition at line 319 of file TypePrinter.h.
References caffe_mnist_image_extractor::str.
|
inline |
Converts a GEMMLowpOutputStageInfo to string.
| [in] | gemm_info | GEMMLowpOutputStageInfo value to be converted |
Definition at line 2715 of file TypePrinter.h.
References caffe_mnist_image_extractor::str.
|
inline |
Converts a GEMMLowpOutputStageType to string.
| [in] | gemm_type | GEMMLowpOutputStageType value to be converted |
Definition at line 2679 of file TypePrinter.h.
References arm_compute::mlgo::parser::gemm_type(), and caffe_mnist_image_extractor::str.
|
inline |
Formatted output of the GEMMReshapeInfo type.
| [in] | info | Type to output. |
Definition at line 1483 of file TypePrinter.h.
References arm_compute::test::validation::info, and caffe_mnist_image_extractor::str.
|
inline |
Formatted output of the GEMMRHSMatrixInfo type.
| [in] | gemm_info | GEMMRHSMatrixInfo to output. |
Definition at line 306 of file TypePrinter.h.
References caffe_mnist_image_extractor::str.
|
inline |
Formatted output of the GenerateProposalsInfo type.
| [in] | proposals_info | Type to output. |
Definition at line 419 of file TypePrinter.h.
References caffe_mnist_image_extractor::str.
|
inline |
Formatted output of the GPUTarget type.
| [in] | gpu_target | Type to output |
Definition at line 2325 of file TypePrinter.h.
References caffe_mnist_image_extractor::str.
|
inline |
Formatted output of the InterpolationPolicy type.
| [in] | policy | Type to output. |
Definition at line 1689 of file TypePrinter.h.
References caffe_mnist_image_extractor::str.
|
inline |
Formatted output of the ITensorInfo type obtained from const ITensor* type.
| [in] | tensor | Type to output. |
Definition at line 1240 of file TypePrinter.h.
References CLTensor::info(), caffe_mnist_image_extractor::str, and tensor.
|
inline |
Formatted output of the const ITensorInfo& type.
| [in] | info | Type to output. |
Definition at line 1198 of file TypePrinter.h.
References arm_compute::test::validation::info, and caffe_mnist_image_extractor::str.
|
inline |
Formatted output of the const ITensorInfo* type.
| [in] | info | Type to output. |
Definition at line 1211 of file TypePrinter.h.
References arm_compute::test::validation::info, and caffe_mnist_image_extractor::str.
| std::string arm_compute::to_string | ( | const LSTMParams< T > & | lstm_params | ) |
Converts a LSTMParams to string.
| [in] | lstm_params | LSTMParams<T> value to be converted |
Definition at line 3037 of file TypePrinter.h.
References caffe_mnist_image_extractor::str.
|
inline |
Formatted output of the Multiples type.
| [in] | multiples | Type to output. |
Definition at line 1676 of file TypePrinter.h.
References caffe_mnist_image_extractor::str.
|
inline |
Converts a NMSType to string.
| [in] | nms_type | NMSType value to be converted |
Definition at line 3089 of file TypePrinter.h.
References caffe_mnist_image_extractor::str.
|
inline |
Formatted output of the Norm Type.
| [in] | type | Type to output. |
Definition at line 1960 of file TypePrinter.h.
References caffe_mnist_image_extractor::str, and type.
|
inline |
Converts a Padding2D to string.
| [in] | padding2d | Padding2D value to be converted |
Definition at line 3285 of file TypePrinter.h.
References caffe_mnist_image_extractor::str.
|
inline |
Converts a Padding3D to string.
| [in] | padding3d | Padding3D value to be converted |
Definition at line 2049 of file TypePrinter.h.
References caffe_mnist_image_extractor::str.
|
inline |
Formatted output of the PaddingList type.
| [in] | padding | Type to output. |
Definition at line 1663 of file TypePrinter.h.
References caffe_mnist_image_extractor::str.
|
inline |
Formatted output of the PaddingMode type.
| [in] | mode | Type to output. |
Definition at line 1594 of file TypePrinter.h.
References clang_tidy_rules::mode, and caffe_mnist_image_extractor::str.
|
inline |
Formatted output of the PadStrideInfo type.
| [in] | pad_stride_info | Type to output. |
Definition at line 1624 of file TypePrinter.h.
References caffe_mnist_image_extractor::str.
|
inline |
Converts a PixelValue to string.
| [in] | pixel_value | PixelValue value to be converted |
Definition at line 2772 of file TypePrinter.h.
References caffe_mnist_image_extractor::str.
|
inline |
Formatted output of the Pooling 3d Layer Info.
| [in] | info | Type to output. |
Definition at line 2110 of file TypePrinter.h.
References arm_compute::test::validation::info, and caffe_mnist_image_extractor::str.
|
inline |
Formatted output of the Pooling Layer Info.
| [in] | info | Type to output. |
Definition at line 1986 of file TypePrinter.h.
References ScaleKernelInfo::data_layout, arm_compute::test::validation::info, and caffe_mnist_image_extractor::str.
|
inline |
Formatted output of the Pooling Type.
| [in] | type | Type to output. |
Definition at line 1973 of file TypePrinter.h.
References caffe_mnist_image_extractor::str, and type.
|
inline |
Formatted output of the PriorBoxLayerInfo.
| [in] | info | Type to output. |
Definition at line 2123 of file TypePrinter.h.
References arm_compute::test::validation::info, and caffe_mnist_image_extractor::str.
|
inline |
Formatted output of the QuantizationInfo type.
| [in] | quantization_info | Type to output. |
Definition at line 447 of file TypePrinter.h.
References caffe_mnist_image_extractor::str.
|
inline |
Formatted output of the Reduction Operations.
| [in] | op | Type to output. |
Definition at line 1843 of file TypePrinter.h.
References caffe_mnist_image_extractor::str.
|
inline |
Formatted output of the ROIPoolingInfo type.
| [in] | pool_info | Type to output. |
Definition at line 240 of file TypePrinter.h.
References caffe_mnist_image_extractor::str.
|
inline |
Formatted output of RoundingPolicy.
| [in] | rounding_policy | Type to output. |
Definition at line 681 of file TypePrinter.h.
References caffe_mnist_image_extractor::str.
|
inline |
Formatted output of the SamplingPolicy type.
| [in] | policy | Type to output. |
Definition at line 1702 of file TypePrinter.h.
References caffe_mnist_image_extractor::str.
|
inline |
Converts a ScaleKernelInfo to string.
| [in] | scale_info | ScaleKernelInfo value to be converted |
Definition at line 2804 of file TypePrinter.h.
References caffe_mnist_image_extractor::str.
|
inline |
Formatted output of the Size2D type.
| [in] | type | Type to output |
Definition at line 2155 of file TypePrinter.h.
References caffe_mnist_image_extractor::str, and type.
|
inline |
Formatted output of the Size3D type.
| [in] | type | Type to output |
Definition at line 2022 of file TypePrinter.h.
References caffe_mnist_image_extractor::str, and type.
|
inline |
Converts a SoftmaxKernelInfo to string.
| [in] | info | SoftmaxKernelInfo value to be converted |
Definition at line 2987 of file TypePrinter.h.
References arm_compute::test::validation::info, and caffe_mnist_image_extractor::str.
|
inline |
Formatted output of the std::tuple<TensorShape, TensorShape, arm_compute::WeightFormat> tuple.
| [in] | values | tuple of input and output tensor shapes and WeightFormat used. |
Definition at line 3254 of file TypePrinter.h.
References caffe_mnist_image_extractor::str.
| std::string arm_compute::to_string | ( | const std::vector< T > & | args | ) |
Formatted output of a vector of objects.
| [in] | args | Vector of objects to print |
Definition at line 148 of file TypePrinter.h.
References GemmTuner::args, and caffe_mnist_image_extractor::str.
|
inline |
Formatted output of the Strides type.
| [in] | stride | Type to output. |
Definition at line 1353 of file TypePrinter.h.
References caffe_mnist_image_extractor::str.
|
inline |
Fallback method: try to use std::to_string:
| [in] | val | Value to convert to string |
Definition at line 94 of file TypePrinter.h.
References arm_compute::support::cpp11::to_string().
|
inline |
Formatted output of the const TensorInfo& type.
| [in] | info | Type to output. |
Definition at line 1185 of file TypePrinter.h.
References arm_compute::test::validation::info, and caffe_mnist_image_extractor::str.
|
inline |
Formatted output of the TensorShape type.
| [in] | shape | Type to output. |
Definition at line 1366 of file TypePrinter.h.
References arm_compute::test::validation::shape, and caffe_mnist_image_extractor::str.
|
inline |
Converts a LSTMParams to string.
| [in] | num | uint8_t value to be converted |
Definition at line 3050 of file TypePrinter.h.
References to_string().
|
inline |
Formatted output of the arm_compute::WeightFormat type.
| [in] | wf | arm_compute::WeightFormat Type to output. |
Definition at line 3186 of file TypePrinter.h.
References __CASE_WEIGHT_FORMAT, ANY, OHWI, OHWIo128, OHWIo16, OHWIo16i2, OHWIo16i2_bf16, OHWIo16i4, OHWIo16i4_bf16, OHWIo16i8, OHWIo2, OHWIo2i8, OHWIo32, OHWIo32i2, OHWIo32i2_bf16, OHWIo32i4, OHWIo32i4_bf16, OHWIo32i8, OHWIo4, OHWIo4i2, OHWIo4i2_bf16, OHWIo4i4, OHWIo4i4_bf16, OHWIo4i8, OHWIo64, OHWIo64i2, OHWIo64i2_bf16, OHWIo64i4, OHWIo64i4_bf16, OHWIo64i8, OHWIo8, OHWIo8i2, OHWIo8i2_bf16, OHWIo8i4, OHWIo8i4_bf16, OHWIo8i8, and UNSPECIFIED.
|
inline |
Formatted output of the WeightsInfo type.
| [in] | info | Type to output. |
Definition at line 1470 of file TypePrinter.h.
References arm_compute::test::validation::info, and caffe_mnist_image_extractor::str.
|
inline |
Formatted output of the Window& type.
| [in] | win | Type to output. |
Definition at line 1521 of file TypePrinter.h.
References caffe_mnist_image_extractor::str.
|
inline |
Formatted output of the Window::Dimension type.
| [in] | dim | Type to output. |
Definition at line 1509 of file TypePrinter.h.
References caffe_mnist_image_extractor::str.
|
inline |
Definition at line 2506 of file TypePrinter.h.
References caffe_mnist_image_extractor::str, and type.
|
inline |
Formatted output of the ITensorInfo type obtained from the ITensor& type.
| [in] | tensor | Type to output. |
Definition at line 1269 of file TypePrinter.h.
References CLTensor::info(), caffe_mnist_image_extractor::str, and tensor.
|
inline |
Formatted output of the ITensorInfo type obtained from the ITensor* type.
| [in] | tensor | Type to output. |
Definition at line 1258 of file TypePrinter.h.
References tensor, and to_string().
|
inline |
Formatted output of the ITensorInfo* type.
| [in] | info | Type to output. |
Definition at line 1229 of file TypePrinter.h.
References arm_compute::test::validation::info, and to_string().
|
inline |
Formatted output of the Window* type.
| [in] | win | Type to output. |
Definition at line 1534 of file TypePrinter.h.
References caffe_mnist_image_extractor::str.
| std::string arm_compute::to_string_if_not_null | ( | T * | arg | ) |
Formatted output if arg is not null.
| [in] | arg | Object to print |
Definition at line 75 of file TypePrinter.h.
References to_string().
|
inline |
Converts a string to a strong types enumeration CLTunerMode.
| [in] | name | String to convert |
Definition at line 57 of file CLTunerTypes.h.
References EXHAUSTIVE, name, NORMAL, RAPID, and arm_compute::utility::tolower().
Referenced by operator>>().
| bool arm_compute::update_window_and_padding | ( | Window & | win, |
| Ts &&... | patterns | ||
| ) |
Update window and padding size for each of the access patterns.
First the window size is reduced based on all access patterns that are not allowed to modify the padding of the underlying tensor. Then the padding of the remaining tensors is increased to match the window.
| [in] | win | Window that is used by the kernel. |
| [in] | patterns | Access patterns used to calculate the final window and padding. |
Definition at line 46 of file WindowHelpers.h.
References arm_compute::utility::for_each(), and arm_compute::test::validation::w.
Referenced by ICLSimpleKernel::configure(), NEBitwiseNotKernel::configure(), NEBitwiseOrKernel::configure(), NEBitwiseXorKernel::configure(), and NEBitwiseAndKernel::configure().
| std::string upper_string | ( | const std::string & | val | ) |
Raise a given string to upper case.
| [in] | val | Given string to lower. |
Definition at line 45 of file StringUtils.cpp.
Referenced by ClMatMulLowpNativeMMULKernel::configure(), ClWidthConcatenate2TensorsKernel::configure(), ClHeightConcatenateKernel::configure(), ClWidthConcatenateKernel::configure(), ClWidthConcatenate4TensorsKernel::configure(), ClMatMulNativeKernel::configure(), ClDepthConcatenateKernel::configure(), ClBatchConcatenateKernel::configure(), ClMatMulLowpNativeKernel::configure(), ClGemmLowpMatrixMultiplyNativeKernel::configure(), ClGemmMatrixMultiplyNativeKernel::configure(), ClGemmLowpQuantizeDownInt32ScaleByFixedPointKernel::configure(), ClGemmMatrixMultiplyReshapedOnlyRhsMMULKernel::configure(), ClIndirectConv2dAddressPrecalculationKernel::configure(), ClWinogradFilterTransformKernel::configure(), ClWinogradInputTransformKernel::configure(), ClIndirectConv2dKernel::configure(), ClGemmLowpQuantizeDownInt32ScaleByFloatKernel::configure(), ClGemmLowpQuantizeDownInt32ScaleKernel::configure(), ClWinogradOutputTransformKernel::configure(), ClGemmLowpMatrixMultiplyReshapedKernel::configure(), ClGemmLowpOffsetContributionOutputStageKernel::configure(), ClGemmLowpOffsetContributionKernel::configure(), ClGemmLowpMatrixMultiplyReshapedOnlyRhsKernel::configure(), ClMatMulNativeMMULKernel::configure(), ClGemmMatrixMultiplyReshapedOnlyRhsKernel::configure(), ClGemmLowpMatrixAReductionKernel::configure(), ClGemmMatrixMultiplyReshapedKernel::configure(), and ClGemmLowpMatrixBReductionKernel::configure().
| Status arm_compute::validate | ( | const ITensorInfo * | scores_in, |
| const ITensorInfo * | boxes_in, | ||
| const ITensorInfo * | batch_splits_in, | ||
| const ITensorInfo * | scores_out, | ||
| const ITensorInfo * | boxes_out, | ||
| const ITensorInfo * | classes, | ||
| const ITensorInfo * | batch_splits_out, | ||
| const ITensorInfo * | keeps, | ||
| const ITensorInfo * | keeps_size, | ||
| const BoxNMSLimitInfo | info | ||
| ) |
Definition at line 243 of file CPPBoxWithNonMaximaSuppressionLimit.cpp.
References ARM_COMPUTE_RETURN_ERROR_ON, ARM_COMPUTE_RETURN_ERROR_ON_DATA_TYPE_CHANNEL_NOT_IN, ARM_COMPUTE_RETURN_ERROR_ON_MISMATCHING_DATA_TYPES, ARM_COMPUTE_RETURN_ERROR_ON_MISMATCHING_QUANTIZATION_INFO, ARM_COMPUTE_RETURN_ERROR_ON_NULLPTR, ARM_COMPUTE_UNUSED, ITensorInfo::data_type(), F16, F32, arm_compute::test::validation::info, UniformQuantizationInfo::offset, QASYMM16, QASYMM8, QASYMM8_SIGNED, ITensorInfo::quantization_info(), UniformQuantizationInfo::scale, and QuantizationInfo::uniform().
Referenced by ClScatter::configure(), ClMatMul::configure(), CpuGemm::configure(), arm_compute::test::validation::FIXTURE_DATA_TEST_CASE(), CpuDepthwiseConv2d::get_depthwiseconvolution_function(), arm_compute::utils::run_example(), arm_compute::test::validation::TEST_CASE(), CPPSplit< CLSlice, ICLTensor >::validate(), CpuDepthwiseConv2d::validate(), ClDirectConv2d::validate(), CLSynthetizeOperator< ClGemmMatrixMultiplyReshapedOnlyRhsKernel >::validate(), NESynthetizeFunction< K >::validate(), ClIndirectConv2d::validate(), CLSynthetizeFunction< K >::validate(), NEQLSTMLayer::validate(), CLQLSTMLayer::validate(), arm_compute::graph::backends::detail::validate_arg_min_max_layer(), arm_compute::graph::backends::detail::validate_bounding_box_transform_layer(), arm_compute::graph::backends::detail::validate_channel_shuffle_layer(), arm_compute::graph::backends::detail::validate_convolution_layer(), arm_compute::graph::backends::detail::validate_depth_to_space_layer(), arm_compute::graph::backends::detail::validate_depthwise_convolution_layer(), arm_compute::graph::backends::detail::validate_dequantization_layer(), arm_compute::graph::backends::detail::validate_detection_output_layer(), arm_compute::graph::backends::detail::validate_detection_post_process_layer(), arm_compute::graph::backends::detail::validate_eltwise_Layer(), arm_compute::graph::backends::detail::validate_generate_proposals_layer(), arm_compute::graph::backends::detail::validate_l2_normalize_layer(), arm_compute::graph::backends::detail::validate_normalize_planar_yuv_layer(), arm_compute::graph::backends::detail::validate_pad_layer(), arm_compute::graph::backends::detail::validate_permute_layer(), arm_compute::graph::backends::detail::validate_prelu_layer(), arm_compute::graph::backends::detail::validate_priorbox_layer(), arm_compute::graph::backends::detail::validate_quantization_layer(), arm_compute::graph::backends::detail::validate_reduction_operation_layer(), arm_compute::graph::backends::detail::validate_reorg_layer(), arm_compute::graph::backends::detail::validate_reshape_layer(), arm_compute::graph::backends::detail::validate_roi_align_layer(), arm_compute::graph::backends::detail::validate_slice_layer(), arm_compute::graph::backends::detail::validate_strided_slice_layer(), and arm_compute::graph::backends::detail::validate_unary_eltwise_layer().
|
inline |
Dequantize a neon vector holding 16 16-bit quantized values.
| [in] | qv | Input values to be dequantized. |
| [in] | qi | Quantization information to be used in the computation. |
Definition at line 171 of file NESymm.h.
References UniformQuantizationInfo::scale, and arm_compute::test::validation::scale.
|
inline |
|
inline |
Dequantize a neon vector holding 16 signed quantized values.
| [in] | qv | Input values to be dequantized. |
| [in] | qi | Quantization information to be used in the computation. |
Definition at line 482 of file NEAsymm.h.
References UniformQuantizationInfo::offset, offset(), UniformQuantizationInfo::scale, and arm_compute::test::validation::scale.
|
inline |
Dequantize following a symmetric quantization scheme a neon vector holding 16 quantized values.
| [in] | qv | Input values to be dequantized. |
| [in] | scale | Quantization scaling factor. |
Definition at line 572 of file NEAsymm.h.
References arm_compute::test::validation::scale.
|
inline |
Dequantize a vector of 16 values stored as signed asymmetric.
| [in] | qv | Input values to be dequantized. |
| [in] | scale | Quantization scaling factor. |
| [in] | offset | Zero quantization offset. |
Definition at line 534 of file NEAsymm.h.
References offset(), and arm_compute::test::validation::scale.
|
inline |
Dequantize a neon vector holding 8 singed quantized values.
| [in] | qv | Input values to be dequantized. |
| [in] | qi | Quantization information to be used in the computation. |
Definition at line 432 of file NEAsymm.h.
References UniformQuantizationInfo::offset, offset(), UniformQuantizationInfo::scale, and arm_compute::test::validation::scale.
|
inline |
Dequantize a neon vector holding 16 quantized values.
| [in] | qv | Input values to be dequantized. |
| [in] | qi | Quantization information to be used in the computation. |
Definition at line 452 of file NEAsymm.h.
References UniformQuantizationInfo::offset, offset(), UniformQuantizationInfo::scale, and arm_compute::test::validation::scale.
|
inline |
Dequantize following an asymmetric quantization scheme a neon vector holding 16 quantized values.
| [in] | qv | Input values to be dequantized. |
| [in] | scale | Quantization scaling factor. |
| [in] | offset | Zero quantization offset. |
Definition at line 505 of file NEAsymm.h.
References offset(), and arm_compute::test::validation::scale.
|
inline |
Dequantize a neon vector holding 8 quantized values.
| [in] | qv | Input values to be dequantized. |
| [in] | qi | Quantization information to be used in the computation. |
Definition at line 410 of file NEAsymm.h.
References UniformQuantizationInfo::offset, offset(), UniformQuantizationInfo::scale, and arm_compute::test::validation::scale.
Referenced by arm_compute::cpu::elementwise_comp_quantized_signed(), arm_compute::cpu::elementwise_op< int8_t >(), arm_compute::cpu::elementwise_op< uint8_t >(), arm_compute::cpu::elementwise_op_quantized(), arm_compute::cpu::elementwise_op_quantized_signed(), arm_compute::cpu::neon_qasymm8_activation(), arm_compute::cpu::neon_qasymm8_signed_activation(), CpuConcatenateWidthKernel::run_op(), and CpuConcatenateHeightKernel::run_op().
|
inline |
Dequantize a neon vector holding 8 16-bit quantized values.
| [in] | qv | Input values to be dequantized. |
| [in] | scale | Quantization scale |
Definition at line 135 of file NESymm.h.
References arm_compute::test::validation::scale.
Referenced by arm_compute::cpu::neon_qsymm16_activation().
| float32x4_t arm_compute::verfq_f32 | ( | float32x4_t | x | ) |
Calculate error function.
| [in] | x | Input vector in F32 format. |
| float32x4_t arm_compute::vexpq_f32 | ( | float32x4_t | x | ) |
Calculate exponential.
| [in] | x | Input vector value in F32 format. |
Referenced by arm_compute::cpu::neon_softmax_non_x_quantized(), and arm_compute::cpu::neon_softmax_x_quantized().
| float32x4_t arm_compute::vfloorq_f32 | ( | float32x4_t | val | ) |
Calculate floor of a vector.
| [in] | val | Input vector value in F32 format. |
Referenced by arm_compute::cpu::fp32_neon_floor().
| float32x2_t arm_compute::vinv_f32 | ( | float32x2_t | x | ) |
Calculate reciprocal.
| [in] | x | Input value. |
| float32x4_t arm_compute::vinvq_f32 | ( | float32x4_t | x | ) |
Calculate reciprocal.
| [in] | x | Input value. |
| float32x2_t arm_compute::vinvsqrt_f32 | ( | float32x2_t | x | ) |
Calculate inverse square root.
| [in] | x | Input value. |
| float32x4_t arm_compute::vinvsqrtq_f32 | ( | float32x4_t | x | ) |
Calculate inverse square root.
| [in] | x | Input value. |
| float32x4_t arm_compute::vlogq_f32 | ( | float32x4_t | x | ) |
Calculate logarithm.
| [in] | x | Input vector value in F32 format. |
| float32x4x2_t arm_compute::vmax2q_f32 | ( | float32x4x2_t | a, |
| float32x4x2_t | b | ||
| ) |
Compute lane-by-lane maximum between elements of a float vector with 4x2 elements.
| [in] | a | Float input vector |
| [in] | b | Float input vector |
|
inline |
Perform a multiply-accumulate on all 16 components of a QASYMM8 vector.
vd*vs + vo
| [in] | vd | Input vector value in QASYMM8 format |
| [in] | vs | Vector multiplier in F32 format. The multiplier value must be duplicated across all four lanes. |
| [in] | vo | Vector addend in F32 format. The addend value must be duplicated across all four lanes. |
Definition at line 30 of file NEAsymm.inl.
References TO_NEAREST_EVEN, and TO_NEAREST_UP.
|
inline |
Perform a multiply-accumulate on all 16 components of a QASYMM8_SIGNED vector.
vd*vs + vo
| [in] | vd | Input vector value in QASYMM8_SIGNED format |
| [in] | vs | Vector multiplier in F32 format. The multiplier value must be duplicated across all four lanes. |
| [in] | vo | Vector addend in F32 format. The addend value must be duplicated across all four lanes. |
Definition at line 90 of file NEAsymm.inl.
References TO_NEAREST_EVEN, and TO_NEAREST_UP.
| float32x4_t arm_compute::vpowq_f32 | ( | float32x4_t | val, |
| float32x4_t | n | ||
| ) |
Calculate n power of a number.
pow(x,n) = e^(n*log(x))
| [in] | val | Input vector value in F32 format. |
| [in] | n | Powers to raise the input to. |
|
inline |
Quantize a neon vector holding 8 floating point values.
| [in] | qv | Input values to be quantized. |
| [in] | qi | Quantization information to be used in the computation. |
Definition at line 591 of file NEAsymm.h.
References UniformQuantizationInfo::offset, offset(), UniformQuantizationInfo::scale, and arm_compute::test::validation::scale.
Referenced by arm_compute::cpu::elementwise_op< uint8_t >(), arm_compute::cpu::neon_qasymm8_activation(), CpuConcatenateHeightKernel::run_op(), and CpuConcatenateWidthKernel::run_op().
|
inline |
Quantize a neon vector holding 16 floating point values.
| [in] | qv | Input values to be quantized. |
| [in] | qi | Quantization information to be used in the computation. |
Definition at line 661 of file NEAsymm.h.
References UniformQuantizationInfo::offset, UniformQuantizationInfo::scale, and vquantize_internal().
|
inline |
Quantize a neon vector holding 8 floating point values.
| [in] | qv | Input values to be quantized. |
| [in] | scale | Quantization scale |
Definition at line 150 of file NESymm.h.
References arm_compute::test::validation::scale.
Referenced by arm_compute::cpu::neon_qsymm16_activation().
|
inline |
Definition at line 634 of file NEAsymm.h.
References offset(), and arm_compute::test::validation::scale.
Referenced by vquantize(), vquantize_qasymm16(), and vquantize_signed().
|
inline |
Quantize to QASYMM16 a neon vector holding 16 floating point values.
| [in] | qv | Input values to be quantized. |
| [in] | qi | Quantization information to be used in the computation. |
Definition at line 691 of file NEAsymm.h.
References UniformQuantizationInfo::offset, UniformQuantizationInfo::scale, and vquantize_internal().
|
inline |
Quantize a neon vector holding 16 floating point values.
| [in] | qv | Input values to be quantized. |
| [in] | qi | Quantization information to be used in the computation. |
Definition at line 191 of file NESymm.h.
References ARM_COMPUTE_ERROR_ON, UniformQuantizationInfo::scale, and arm_compute::test::validation::scale.
|
inline |
Quantize a neon vector holding 8 floating point values.
| [in] | qv | Input values to be quantized. |
| [in] | qi | Quantization information to be used in the computation. |
Definition at line 616 of file NEAsymm.h.
References UniformQuantizationInfo::offset, offset(), UniformQuantizationInfo::scale, and arm_compute::test::validation::scale.
Referenced by arm_compute::cpu::elementwise_op< int8_t >(), arm_compute::cpu::neon_qasymm8_signed_activation(), CpuConcatenateHeightKernel::run_op(), and CpuConcatenateWidthKernel::run_op().
|
inline |
Signed quantize a neon vector holding 16 floating point values.
| [in] | qv | Input values to be quantized. |
| [in] | qi | Quantization information to be used in the computation. |
Definition at line 676 of file NEAsymm.h.
References UniformQuantizationInfo::offset, UniformQuantizationInfo::scale, and vquantize_internal().
|
inline |
Reduce a vector to be a scalar by accumulating all lanes in the vector.
| [in] | v | Vector to be reduced. |
Definition at line 537 of file NEMath.inl.
References arm_compute::test::validation::b.
Referenced by arm_compute::cpu::kernels::convolve_nchw(), arm_compute::cpu::kernels::convolve_nhwc(), and arm_compute::cpu::directconv3d_float_neon_ndhwc().
| float32x4_t arm_compute::vroundq_rte_f32 | ( | float32x4_t | val | ) |
Calculate round value of a vector to nearest with ties to even.
| [in] | val | Input vector value in F32 format. |
| float32x2_t arm_compute::vsin_f32 | ( | float32x2_t | val | ) |
Calculate sine.
| [in] | val | Input vector value in radians, F32 format. |
| float32x4_t arm_compute::vsinq_f32 | ( | float32x4_t | val | ) |
Calculate sine.
| [in] | val | Input vector value in radians, F32 format. |
| float32x4_t arm_compute::vtanhq_f32 | ( | float32x4_t | val | ) |
Calculate hyperbolic tangent.
tanh(x) = (e^2x - 1)/(e^2x + 1)
| [in] | val | Input vector value in F32 format. |
| float32x4_t arm_compute::vtaylor_polyq_f32 | ( | float32x4_t | x, |
| const std::array< float32x4_t, 8 > & | coeffs | ||
| ) |
Perform a 7th degree polynomial approximation using Estrin's method.
| [in] | x | Input vector value in F32 format. |
| [in] | coeffs | Polynomial coefficients table. |
|
inline |
Wrap-around a number within the range 0 <= x < m.
| [in] | x | Input value |
| [in] | m | Range |
Definition at line 277 of file Helpers.h.
Referenced by SplitLayerNode::compute_output_descriptor(), ClSoftmaxKernel::configure(), CLGatherKernel::configure(), CpuSoftmaxGeneric::configure(), CLL2NormalizeLayerKernel::configure(), NEStackLayer::configure(), NEL2NormalizeLayer::configure(), CLStackLayer::configure(), CLL2NormalizeLayer::configure(), SplitLayerNode::configure_output(), convert_negative_axis(), arm_compute::test::validation::reference::softmax_layer_generic(), arm_compute::test::validation::reference::unstack(), SplitLayerNode::validate(), CpuSoftmaxGeneric::validate(), NEStackLayer::validate(), NEL2NormalizeLayer::validate(), CLStackLayer::validate(), CLL2NormalizeLayer::validate(), and GpuSoftmax::validate_op().
| const std::array< ErfLutEntry< float >, 513 > erf_f32_lut |
| const std::array<float32x4_t, 8> log_tab |
Logarithm polynomial coefficients.
Definition at line 34 of file NEMath.inl.
|
constexpr |
Constant value used to indicate maximum dimensions of a Window, TensorShape and Coordinates.
Definition at line 38 of file Dimensions.h.
Referenced by arm_compute::misc::shape_calculator::calculate_concatenate_shape().
|
constexpr |
Sin polynomial coefficients.
Definition at line 46 of file NEMath.inl.
|
constexpr |
Definition at line 47 of file NEMath.inl.
|
constexpr |
Definition at line 48 of file NEMath.inl.
|
constexpr |
Definition at line 49 of file NEMath.inl.
1.8.17