我有一个相当复杂的程序，在 MSVC 2010 Debug模式下使用 OpenMP 构建时会遇到奇怪的行为。我已尽力构建以下最小的工作示例(尽管它不是真正最小的)，它缩小了真实程序的结构。

#include <vector>
#include <cassert>

// A class take points to the whole collection and a position Only allow access
// to the elements at that posiiton. It provide read-only access to query some
// information about the whole collection
class Element
{
    public :

    Element (int i, std::vector<double> *src) : i_(i), src_(src) {}

    int i () const {return i_;}
    int size () const {return src_->size();}

    double src () const {return (*src_)[i_];}
    double &src () {return (*src_)[i_];}

    private :

    const int i_;
    std::vector<double> *const src_;
};

// A Base class for dispatch
template <typename Derived>
class Base
{
    protected :

    void eval (int dim, Element elem, double *res)
    {
        // Dispatch the call from Evaluation<Derived>
        eval_dispatch(dim, elem, res, &Derived::eval); // Point (2)
    }

    private :

    // Resolve to Derived non-static member eval(...)
    template <typename D>
    void eval_dispatch(int dim, Element elem, double *res,
            void (D::*) (int, Element, double *))
    {
#ifndef NDEBUG // Assert that this is a Derived object
        assert((dynamic_cast<Derived *>(this)));
#endif
        static_cast<Derived *>(this)->eval(dim, elem, res);
    }

    // Resolve to Derived static member eval(...)
    void eval_dispatch(int dim, Element elem, double *res,
            void (*) (int, Element, double *))
    {
        Derived::eval(dim, elem, res); // Point (3)
    }

    // Resolve to Base member eval(...), Derived has no this member but derived
    // from Base
    void eval_dispatch(int dim, Element elem, double *res,
            void (Base::*) (int, Element, double *))
    {
        // Default behavior: do nothing
    }
};

// A middle-man who provides the interface operator(), call Base::eval, and
// Base dispatch it to possible default behavior or Derived::eval
template <typename Derived>
class Evaluator : public Base<Derived>
{
    public :

    void operator() (int N , int dim, double *res)
    {
        std::vector<double> src(N);
        for (int i = 0; i < N; ++i)
            src[i] = i;

#pragma omp parallel for default(none) shared(N, dim, src, res)
        for (int i = 0; i < N; ++i) {
            assert(i < N);
            double *r = res + i * dim;
            Element elem(i, &src);
            assert(elem.i() == i); // Point (1)
            this->eval(dim, elem, r);
        }
    }
};

// Client code, who implements eval
class Implementation : public Evaluator<Implementation>
{
    public :

    static void eval (int dim, Element elem, double *r)
    {
        assert(elem.i() < elem.size()); // This is where the program fails Point (4)
        for (int d = 0; d != dim; ++d)
            r[d] = elem.src();
    }
};

int main ()
{
    const int N = 500000;
    const int Dim = 2;
    double *res = new double[N * Dim];
    Implementation impl;
    impl(N, Dim, res);
    delete [] res;

    return 0;
}

最佳答案

显然，MSVC 中的 64 位 OpenMP 实现与未经优化编译的代码不兼容。

为了调试您的问题，我修改了您的代码以将迭代编号保存到 threadprivate调用 this->eval() 之前的全局变量然后在Implementation::eval()的开头加了一个check查看保存的迭代次数是否与 elem.i_ 不同:

static int _iter;
#pragma omp threadprivate(_iter)

...
#pragma omp parallel for default(none) shared(N, dim, src, res)
    for (int i = 0; i < N; ++i) {
        assert(i < N);
        double *r = res + i * dim;
        Element elem(i, &src);
        assert(elem.i() == i); // Point (1)
        _iter = i;             // Save the iteration number
        this->eval(dim, elem, r);
    }
}
...

...
static void eval (int dim, Element elem, double *r)
{
    // Check for difference
    if (elem.i() != _iter)
        printf("[%d] _iter=%x != %x\n", omp_get_thread_num(), _iter, elem.i());
    assert(elem.i() < elem.size()); // This is where the program fails Point (4)
    for (int d = 0; d != dim; ++d)
        r[d] = elem.src();
}
...

#pragma omp parallel for default(none) shared(N, dim, src, res)
    for (int i = 0; i < N; ++i) {
        ...
#pragma omp critical
        this->eval(dim, elem, r);
    }
}

this->eval(dim, elem, r);

...
void eval (int dim, Element elem, double *res)
{
    printf("[%d] In Base::eval()    &elem = %p\n", omp_get_thread_num(), &elem);
    // Dispatch the call from Evaluation<Derived>
    eval_dispatch(dim, elem, res, &Derived::eval); // Point (2)
}
...

...
#pragma omp parallel for default(none) shared(N, dim, src, res)
    for (int i = 0; i < N; ++i) {
        ...
        Element elem(i, &src);
        ...
        printf("[%d] In parallel region &elem = %p\n", omp_get_thread_num(), &elem);
        this->eval(dim, elem, r);
    }
}
...

[0] Parallel region &elem = 000000000030F348 (a)
[0] Base::eval()    &elem = 000000000030F630
[0] Parallel region &elem = 000000000030F348 (a)
[0] Base::eval()    &elem = 000000000030F630
[1] Parallel region &elem = 000000000292F9B8 (b)
[1] Base::eval()    &elem = 000000000030F630 <---- !!
[1] Parallel region &elem = 000000000292F9B8 (b)
[1] Base::eval()    &elem = 000000000030F630 <---- !!

void eval (int dim, Element& elem, double *res)
{
    eval_dispatch(dim, elem, res, &Derived::eval); // Point (2)
}

Element (const Element& e) : i_(e.i_), src_(e.src_) {}

关于c++ - 复制对象时，带有 MSVC 2010 Debug 的 OpenMP 会生成奇怪的错误，我们在Stack Overflow上找到一个类似的问题： https://stackoverflow.com/questions/11479337/