Show / Hide Table of Contents

    Enum cudnnReduceTensorOp

    cudnnReduceTensorOp is an enumerated type used to indicate the tensor operation to be used by the cudnnReduceTensor() routine.This enumerated type is used as a field for the cudnnReduceTensorDescriptor_t descriptor.

    Namespace: ManagedCuda.CudaDNN
    Assembly: CudaDNN.dll
    Syntax
    public enum cudnnReduceTensorOp

    Fields

    Name Description
    Add

    The operation to be performed is addition

    AMax

    The operation to be performed is a maximum comparison of absolute values

    Avg

    The operation to be performed is averaging

    Max

    The operation to be performed is a maximum comparison

    Min

    The operation to be performed is a minimum comparison

    Mul

    The operation to be performed is multiplication

    MulNoZeros
    Norm1

    The operation to be performed is addition of absolute values

    Norm2

    The operation to be performed is a square root of sum of squares

    • Improve this Doc
    • View Source
    Back to top Generated by DocFX