Strange performance difference of matrix row summation with RowMajor and ColMajor data arrangement

I decided to check how data arrangement in matrix influences performance of simple operations.I wrote simple row summation algorithm using Eigen::Matrix as data storage.I though that RowMajor storage should demostrate better performance due to better cache utilization.

I used g++ compiler with -O2 option and it gives me following results:

ColMajor: 40791546 µsRowMajor: 28790948 µs

It's pretty ok. But with -O3 it gives me really strange difference:

ColMajor: 10353619 µsRowMajor: 28359348 µs

And it looks like ColMajor becomes really fast with -O3. Why switching from -O2 to -O3 changes performance so drastically?

My CPU: intel i7-6700K, gcc version: 7.5.0-3ubuntu1~19.10

My "benchmark":

#include <iostream>#include <vector>#include <chrono>#include "Eigen/Core"template<typename DerivedMat, typename DerivedRes>void runTest(const Eigen::MatrixBase<DerivedMat> &mat, Eigen::MatrixBase<DerivedRes> &res) {    const int64_t nRows = mat.rows();    const int64_t nCols = mat.cols();    for(int64_t row = 0; row < nRows; ++row){        for(int64_t col = 0; col < nCols; ++col){            res(row, 0) += mat(row, col);        }    }}const int64_t nRows = 300;const int64_t nCols = 5000;const int nAttempts = 20000;template<int Alignment>void bench() {    Eigen::Matrix<float, -1, -1, Alignment> mat(nRows, nCols);    srand(42);    mat.setRandom();    Eigen::VectorXf res(nRows);    res.setZero();    std::chrono::steady_clock::time_point begin = std::chrono::steady_clock::now();    for(int iter = 0; iter < nAttempts; ++iter)        runTest(mat, res);    std::chrono::steady_clock::time_point end = std::chrono::steady_clock::now();    std::cout << "Elapsed "<< std::chrono::duration_cast<std::chrono::microseconds>(end - begin).count() << "[µs]"<< std::endl;}int main() {    bench<Eigen::ColMajor>();    //bench<Eigen::RowMajor>();    return 0;}