int main(int narg, char* args[]) {
Kokkos::initialize(narg,args);
int chunk_size = 1024;
int nchunks = 100000; //1024*1024;
Kokkos::DualView<int*> data("data",nchunks*chunk_size+1);
srand(1231093);
for(int i = 0; i < (int) data.dimension_0(); i++) {
data.h_view(i) = rand()%TEAM_SIZE;
}
data.modify<Host>();
data.sync<Device>();
Kokkos::DualView<int**> histogram("histogram",TEAM_SIZE,TEAM_SIZE);
Kokkos::Timer timer;
// threads/team is automatically limited to maximum supported by the device.
Kokkos::parallel_for( team_policy( nchunks , TEAM_SIZE )
, find_2_tuples(chunk_size,data,histogram) );
Kokkos::fence();
double time = timer.seconds();
histogram.sync<Host>();
printf("Time: %f \n\n",time);
int sum = 0;
for(int k=0; k<TEAM_SIZE; k++) {
for(int l=0; l<TEAM_SIZE; l++) {
printf("%i ",histogram.h_view(k,l));
sum += histogram.h_view(k,l);
}
printf("\n");
}
printf("Result: %i %i\n",sum,chunk_size*nchunks);
Kokkos::finalize();
}
int main(int narg, char* args[]) {
Kokkos::initialize(narg,args);
int chunk_size = 1024;
int nchunks = 100000; //1024*1024;
Kokkos::DualView<int*> data("data",nchunks*chunk_size+1);
srand(1231093);
for(int i = 0; i < data.dimension_0(); i++) {
data.h_view(i) = rand()%TS;
}
data.modify<Host>();
data.sync<Device>();
Kokkos::DualView<int**> histogram("histogram",TS,TS);
Kokkos::Impl::Timer timer;
Kokkos::parallel_for(
Kokkos::ParallelWorkRequest(nchunks,TS<Device::team_max()?TS:Device::team_max()),
find_2_tuples(chunk_size,data,histogram));
Kokkos::fence();
double time = timer.seconds();
histogram.sync<Host>();
printf("Time: %lf \n\n",time);
int sum = 0;
for(int k=0; k<TS; k++) {
for(int l=0; l<TS; l++) {
printf("%i ",histogram.h_view(k,l));
sum += histogram.h_view(k,l);
}
printf("\n");
}
printf("Result: %i %i\n",sum,chunk_size*nchunks);
Kokkos::finalize();
}
