$ cat t1.cpp
#include <iostream>
#include <stdio.h>
#include <time.h>
#include <cblas.h>
//#include <cublas_v2.h>
using namespace std;

int main()
{
const int m = 5000;

timespec blas_start, blas_end;
long totalnsec; //total nano sec
double totalsec, totaltime;
int i, j;
float *A = new float[m]; // 1 x m
float *B = new float[m*m]; // m x m
float *C = new float[m]; // 1 x m

float input;
cout << "Enter a value to populate the vector (0 for sparse) ";
cin >> input; // enter 0 for sparse

// input martix A: every 32nd element is non-zero, rest of the values = input
for(i = 0; i < m; i++)
{
A[i] = input;
if( i % 32 == 0)    //adjust for sparsity
        A[i] = i;
}

// input matrix B: identity matrix
for(i = 0; i < m; i++)
        for(j = 0; j < m; j++)
            B[i*m + j] = (i==j);

clock_gettime(CLOCK_REALTIME, &blas_start);
cblas_sgemm(CblasRowMajor, CblasNoTrans, CblasNoTrans, 1, m, m, 1.0f, A, m, B, m, 0.0f, C, m);
clock_gettime(CLOCK_REALTIME, &blas_end);

/* for(i = 0; i < m; i++)
        printf("%f ", C[i]);
printf("\n\n");    */

// Print time
totalsec = (double)blas_end.tv_sec - (double)blas_start.tv_sec;
totalnsec = blas_end.tv_nsec - blas_start.tv_nsec;
if(totalnsec < 0)
{
    totalnsec += 1e9;
    totalsec -= 1;
}
totaltime = totalsec + (double)totalnsec*1e-9;
cout<<"Duration = "<< totaltime << "\n";

return 0;
}
$ g++ -I/usr/include/openblas t1.cpp -lopenblas -o t1
$ ./t1
Enter a value to populate the vector (0 for sparse) 5
Duration = 0.026064
$ ./t1
Enter a value to populate the vector (0 for sparse) 0
Duration = 0.0260185
$