Thread affinity with Windows, MSVC, and OpenMP
#ifdef _WIN32
HANDLE process;
DWORD_PTR processAffinityMask;
//Windows uses a compact thread topology. Set mask to every other thread
for(int i=0; i<ncores; i++) processAffinityMask |= 1<<(2*i);
process = GetCurrentProcess();
SetProcessAffinityMask(process, processAffinityMask);
#pragma omp parallel
{
HANDLE thread = GetCurrentThread();
DWORD_PTR threadAffinityMask = 1<<(2*omp_get_thread_num());
SetThreadAffinityMask(thread, threadAffinityMask);
}
#else
cpu_set_t mask;
CPU_ZERO(&mask);
for(int i=0; i<ncores; i++) CPU_SET(i, &mask);
sched_setaffinity(0, sizeof(mask), &mask);
#pragma omp parallel
{
cpu_set_t mask;
CPU_ZERO(&mask);
CPU_SET(omp_get_thread_num(),&mask);
pthread_setaffinity_np(pthread_self(), sizeof(mask), &mask);
}
#endif