经过一整天的调试，我意识到这是我代码中的瓶颈。On the documentation it says that there is no SIMD for a.pow() .不管什么原因，实际上在我的机器上，对于300 x 50 Eigen：：ArrayXXd，a * a * a * a似乎更快。

#include <iostream>
#include <chrono>
#include <Eigen/Dense>

int main() {
    Eigen::ArrayXXd m = Eigen::ArrayXd::LinSpaced(300 * 50, 0, 300 * 50 - 1).reshaped(300, 50);

    {
        decltype(m) result; // prevent loop from being eliminated
        auto start = std::chrono::steady_clock::now();
        for (size_t i = 0; i < 100000; i++)
        {
            result = m.square().square();
        }
        auto end = std::chrono::steady_clock::now();
        std::cout << "Per run(microsecond)=" << std::chrono::duration_cast<std::chrono::microseconds>(end - start).count() / 100000.0 << std::endl;
    }

    {
        decltype(m) result; // prevent loop from being eliminated
        auto start = std::chrono::steady_clock::now();
        for (size_t i = 0; i < 100000; i++)
        {
            result = m * m * m * m;
        }
        auto end = std::chrono::steady_clock::now();
        std::cout << "Per run(microsecond)=" << std::chrono::duration_cast<std::chrono::microseconds>(end - start).count() / 100000.0 << std::endl;
    }

    {
        decltype(m) result; // prevent loop from being eliminated
        auto start = std::chrono::steady_clock::now();
        for (size_t i = 0; i < 10000; i++)
        {
            result = m.pow(4);
        }
        auto end = std::chrono::steady_clock::now();
        std::cout << "Per run(microsecond)=" << std::chrono::duration_cast<std::chrono::microseconds>(end - start).count() / 10000.0 << std::endl;
    }

    return 0;

m.square().square();
Per run(microsecond)=17.9101

m * m * m * m;
Per run(microsecond)=10.3267

m.pow(4);
Per run(microsecond)=431.636

对于C++17 if constexpr，这是可能的，否则就不可能了，所以目前，a.pow(x)等价于为每个i调用std::pow(a[i],x)。