矩阵乘法实现

**所需基础知识：矩阵乘法，模板函数

C++代码

//A_mk * B_kn
template<typename T>
int matrixMul(T* out, T* A, T* B, int M, int N, int K)
{
    for (int row = 0; row < M; row++) {
        for (int col = 0; col < N; col++) {
            out[row * M + col] = 0;
            for (int i = 0; i < K; i++) {
                out[row * M + col] += A[row * K + i] * B[i * N + col];
            }
        }
    }
    return 0;
}