class cv::cuda::TargetArchs

Overview

Class providing a set of static methods to check what NVIDIA* card architecture the CUDA module was built for. More…

#include <cuda.hpp>

class TargetArchs
{
public:
    // methods

    static
    bool
    builtWith(FeatureSet feature_set);

    static
    bool
    has(
        int major,
        int minor
        );

    static
    bool
    hasBin(
        int major,
        int minor
        );

    static
    bool
    hasEqualOrGreater(
        int major,
        int minor
        );

    static
    bool
    hasEqualOrGreaterBin(
        int major,
        int minor
        );

    static
    bool
    hasEqualOrGreaterPtx(
        int major,
        int minor
        );

    static
    bool
    hasEqualOrLessPtx(
        int major,
        int minor
        );

    static
    bool
    hasPtx(
        int major,
        int minor
        );
};

Detailed Documentation

Class providing a set of static methods to check what NVIDIA* card architecture the CUDA module was built for.

According to the CUDA C Programming Guide Version 3.2: “PTX code produced for some specific compute capability can always be compiled to binary code of greater or equal compute capability”.

Methods

static
bool
builtWith(FeatureSet feature_set)

The following method checks whether the module was built with the support of the given feature:

Parameters:

feature_set

Features to be checked. See :ocvcuda::FeatureSet.

static
bool
has(
    int major,
    int minor
    )

There is a set of methods to check whether the module contains intermediate (PTX) or binary CUDA code for the given architecture(s):

Parameters:

major	Major compute capability version.
minor	Minor compute capability version.