Reputation:
I am trying to get the runtime of the following code using the clock_gettime function. However when I am running the code I am receiving a time of 0.0000 every time it runs. I have output the start and stop time individually also and I am receiving the exact same answer.
struct timespec start, stop;
double accum;
if( clock_gettime( CLOCK_REALTIME, &start) == -1 ) {
perror( "clock gettime" );
exit( EXIT_FAILURE );
}
int src = 1, final_ret = 0;
for (int t = 0; t < rows - 1; t += pyramid_height)
{
int temp = src;
src = final_ret;
final_ret = temp;
// Calculate this for the kernel argument...
int arg0 = MIN(pyramid_height, rows-t-1);
int theHalo = HALO;
// Set the kernel arguments.
clSetKernelArg(cl.kernel(kn), 0, sizeof(cl_int), (void*) &arg0);
clSetKernelArg(cl.kernel(kn), 1, sizeof(cl_mem), (void*) &d_gpuWall);
clSetKernelArg(cl.kernel(kn), 2, sizeof(cl_mem), (void*) &d_gpuResult[src]);
clSetKernelArg(cl.kernel(kn), 3, sizeof(cl_mem), (void*) &d_gpuResult[final_ret]);
clSetKernelArg(cl.kernel(kn), 4, sizeof(cl_int), (void*) &cols);
clSetKernelArg(cl.kernel(kn), 5, sizeof(cl_int), (void*) &rows);
clSetKernelArg(cl.kernel(kn), 6, sizeof(cl_int), (void*) &t);
clSetKernelArg(cl.kernel(kn), 7, sizeof(cl_int), (void*) &borderCols);
clSetKernelArg(cl.kernel(kn), 8, sizeof(cl_int), (void*) &theHalo);
clSetKernelArg(cl.kernel(kn), 9, sizeof(cl_int) * (cl.localSize()), 0);
clSetKernelArg(cl.kernel(kn), 10, sizeof(cl_int) * (cl.localSize()), 0);
clSetKernelArg(cl.kernel(kn), 11, sizeof(cl_mem), (void*) &d_outputBuffer);
cl.launch(kn);
}
if( clock_gettime( CLOCK_REALTIME, &stop) == -1 ) {
perror( "clock gettime" );
exit( EXIT_FAILURE );
}
printf( "%lf\n", stop.tv_sec );
printf( "%lf\n", start.tv_sec );
accum = ( stop.tv_sec - start.tv_sec )
+ ( stop.tv_nsec - start.tv_nsec )
/ BILLION;
printf( "%lf\n", accum );
Any advice on what I'm doing wrong is much appreciated
Upvotes: 1
Views: 471
Reputation: 171283
timespec::tv_nsec
is an integer type, so if BILLION
is also an integer type then:
( stop.tv_nsec - start.tv_nsec )
/ BILLION;
will truncate to zero. If the tv_sec
values are the same you get a zero difference.
Try:
double( stop.tv_nsec - start.tv_nsec )
/ BILLION;
That will perform the division with a double
type.
Upvotes: 4