CCS/TMS320F28377D: What is the most efficient way to implement matrix products?

Tool/software: Code Composer Studio

I am trying to implement a neural network so I am dealing with a lot of matrix multiplications. I was wondering what is the best and fastest way to implement that? Is there any built-in function for that?

void Mat_Product(float ***M1M2, float M1, float M2, int r1, int c1, int r2, int c2){
    int i,j;
    for (i=0; i<r1;i++){
        for (j=0; j<c2;i++){
            *M1M2[i][j]=1;


            }
    }
}