Enum cudnnConvolutionBwdFilterAlgo

cudnnConvolutionBwdFilterAlgo is an enumerated type that exposes the different algorithms available to execute the backward filter convolution operation.

Namespace: ManagedCuda.CudaDNN

Assembly: CudaDNN.dll

Syntax

public enum cudnnConvolutionBwdFilterAlgo

Fields

Name	Description
Algo0	This algorithm expresses the convolution as a sum of matrix product without actually explicitly form the matrix that holds the input tensor data. The sum is done using atomic adds operation, thus the results are non-deterministic.
Algo1	This algorithm expresses the convolution as a matrix product without actually explicitly form the matrix that holds the input tensor data. The results are deterministic.
Algo3	This algorithm is similar to CUDNN_CONVOLUTION_BWD_FILTER_ALGO_0 but uses some small workspace to precomputes some indices. The results are also non-deterministic.
AlgoFFT	This algorithm uses a Fast-Fourier Transform approach to compute the convolution. A significant memory workspace is needed to store intermediate results. The results are deterministic.
AlgoFFTTiling	This algorithm uses the Fast-Fourier Transform approach to compute the convolution but splits the input tensor into tiles. Significant workspace may be needed to store intermediate results. The results are deterministic.
AlgoWinograd	Not implemented
AlgoWinogradNonFused	This algorithm uses the Winograd Transform approach to compute the convolution. Significant workspace may be needed to store intermediate results. The results are deterministic.