Compute Library
 23.08
arm_compute::opencl::kernels Namespace Reference

Namespaces

 gemm
 

Data Structures

class  ClActivationKernel
 Interface for the activation kernel. More...
 
class  ClArithmeticKernel
 
class  ClBatchConcatenateKernel
 Interface for the batch concatenate kernel. More...
 
class  ClCastKernel
 Casts a given tensor to a new type. More...
 
class  ClCol2ImKernel
 Interface for the col2im reshaping kernel. More...
 
class  ClComplexMulKernel
 Interface for the complex pixelwise multiplication kernel. More...
 
class  ClConvertFullyConnectedWeightsKernel
 
class  ClCopyKernel
 OpenCL kernel to perform a copy between two tensors. More...
 
class  ClCropKernel
 OpenCL kernel to perform a copy between two tensors. More...
 
class  ClDepthConcatenateKernel
 Interface for the depth concatenate kernel. More...
 
class  ClDequantizeKernel
 Interface for the dequantization layer kernel. More...
 
class  ClDirectConv2dKernel
 Interface for the direct convolution kernel. More...
 
class  ClDirectConv3dKernel
 Interface for the direct convolution 3d kernel. More...
 
class  ClElementwiseKernel
 Interface for an element-wise operation kernel. More...
 
class  ClElementWiseUnaryKernel
 Interface for the elementwise unary operator. More...
 
class  ClFillKernel
 Interface for filling the planes of a tensor. More...
 
class  ClFloorKernel
 OpenCL kernel to perform a floor operation. More...
 
class  ClGemmLowpMatrixAReductionKernel
 OpenCL kernel used to compute the row-vectors of sums of all the entries in each row of Matrix A. More...
 
class  ClGemmLowpMatrixBReductionKernel
 OpenCL kernel used to compute the row-vectors of sums of all the entries in each column of Matrix B. More...
 
class  ClGemmLowpMatrixMultiplyNativeKernel
 OpenCL kernel to multiply matrices with QASYMM8/QASYMM8_SIGNED data type. More...
 
class  ClGemmLowpMatrixMultiplyReshapedKernel
 OpenCL kernel to multiply matrices when both the input matrices LHS (src0) and RHS (src1) have been reshaped. More...
 
class  ClGemmLowpMatrixMultiplyReshapedOnlyRhsKernel
 OpenCL kernel to multiply matrices with QASYMM8 data type when only the input matrix RHS (src1) has been reshaped. More...
 
class  ClGemmLowpMatrixMultiplyReshapedOnlyRhsMMULKernel
 OpenCL kernel to multiply matrices with QASYMM8/QASYMM8_SIGNED data types when only the input matrix RHS (src1) has been reshaped using the MMUL instruction. More...
 
class  ClGemmLowpOffsetContributionKernel
 OpenCL kernel used to add the offset contribution after the matrix multiplication. More...
 
class  ClGemmLowpOffsetContributionOutputStageKernel
 OpenCL kernel used to add the offset contribution after the matrix multiplication and perform the output stage. More...
 
class  ClGemmLowpQuantizeDownInt32ScaleByFixedPointKernel
 OpenCL kernel used to quantize down the int32 accumulator values of GEMMLowp to QASYMM8/QASYMM8_SIGNED/QSYMM16. More...
 
class  ClGemmLowpQuantizeDownInt32ScaleByFloatKernel
 OpenCL kernel used to quantize down the int32 accumulator values of GEMMLowp to QASYMM8/QASYMM8_SIGNED. More...
 
class  ClGemmLowpQuantizeDownInt32ScaleKernel
 OpenCL kernel used to quantize down the int32 accumulator values of GEMMLowp to QASYMM8/QASYMM8_SIGNED. More...
 
class  ClGemmMatrixMultiplyNativeKernel
 OpenCL kernel to multiply matrices when neither of the input matrices have been reshaped. More...
 
class  ClGemmMatrixMultiplyReshapedKernel
 OpenCL kernel to multiply matrices when both the input matrices LHS (src0) and RHS (src1) have been reshaped. More...
 
class  ClGemmMatrixMultiplyReshapedOnlyRhsKernel
 OpenCL kernel to multiply matrices when only the input matrix RHS (src1) has been reshaped. More...
 
class  ClGemmMatrixMultiplyReshapedOnlyRhsMMULKernel
 OpenCL kernel to multiply matrices using MMUL when only the input matrix RHS (src1) has been reshaped. More...
 
class  ClGemmReshapeLhsMatrixKernel
 OpenCL kernel to reshape the LHS matrix when performing the matrix multiplication. More...
 
class  ClGemmReshapeRhsMatrixKernel
 OpenCL kernel to reshape the RHS matrix when performing the matrix multiplication In particular, this kernel splits the src matrix in blocks of size K0xN0 and stores each one in the dst matrix unrolling the values. More...
 
class  ClHeightConcatenateKernel
 Interface for the height concatenate kernel. More...
 
class  ClIm2ColKernel
 Interface for the im2col reshape kernel. More...
 
class  ClIndirectConv2dAddressPrecalculationKernel
 Interface for the direct convolution kernel. More...
 
class  ClIndirectConv2dKernel
 Interface for the indirect convolution kernel. More...
 
class  ClLogicalBinaryKernel
 
class  ClLogits1DMaxShiftExpSumKernel
 Interface for max, shifting, exponentiating and summing the logits. More...
 
class  ClLogits1DNormKernel
 Interface for calculating the final step of the Softmax Layer where each logit value is multiplied by the inverse of the sum of the logits. More...
 
class  ClMatMulLowpNativeKernel
 
class  ClMatMulNativeKernel
 
class  ClMatMulNativeMMULKernel
 
class  ClMulKernel
 Interface for the pixelwise multiplication kernel. More...
 
class  ClPermuteKernel
 OpenCL kernel to perform tensor permutation. More...
 
class  ClPool2dKernel
 Interface for the pooling layer kernel. More...
 
class  ClPool3dKernel
 Interface for the pooling layer kernel. More...
 
class  ClQuantizeKernel
 Interface for the quantization layer kernel. More...
 
class  ClReshapeKernel
 Interface for the kernel to perform tensor reshaping. More...
 
class  ClSaturatedArithmeticKernel
 Addition operation. More...
 
class  ClScaleKernel
 Interface for the scale kernel. More...
 
class  ClTransposedConvolutionKernel
 OpenCL kernel for transposed convolution. More...
 
class  ClTransposeKernel
 OpenCL kernel to transpose a 2D tensor. More...
 
class  ClWeightsReshapeKernel
 OpenCL kernel to perform reshaping on the weights used by convolution and locally connected layer. More...
 
class  ClWidthConcatenate2TensorsKernel
 Interface for the width concatenate kernel of 2 tensors. More...
 
class  ClWidthConcatenate4TensorsKernel
 Interface for the width concatenate kernel of 4 tensors. More...
 
class  ClWidthConcatenateKernel
 Interface for the width concatenate kernel. More...
 
class  ClWinogradFilterTransformKernel
 Interface for the Winograd filter transform kernel. More...
 
class  ClWinogradInputTransformKernel
 OpenCL kernel to perform Winograd input transform. More...
 
class  ClWinogradOutputTransformKernel
 Interface for the Winograd output transform kernel. More...
 
class  IClGemmLowpReductionKernel
 Common interface for all OpenCL reduction kernels. More...