GetFEM
5.4.2
|
Tools for multithreaded, OpenMP and Boost based parallelization. More...
Go to the source code of this file.
Classes | |
struct | getfem::true_thread_policy |
Thread policy, where partitioning is based on true threads. More... | |
struct | getfem::global_thread_policy |
Thread policy, regulated by partition_master (can be true thread- or partition-based) More... | |
class | getfem::detail::omp_distribute_impl< std::vector< T >, thread_policy, vector_tag > |
Specialization for std::vector<T>, adds vector indexing operator. More... | |
class | getfem::detail::omp_distribute_impl< bool, thread_policy, bool_tag > |
Specialization for bool, to circumvent the shortcomings of standards library's specialization for std::vector<bool>, we use std::vector<int> instead. More... | |
class | getfem::omp_distribute< T, thread_policy > |
Use this template class for any object you want to distribute to open_MP threads. More... | |
class | getfem::partition_iterator |
Iterator that runs over partitions on the current thread and sets the global (but thread-specific) partition during incrementation. More... | |
class | getfem::partition_master |
A singleton that Manages partitions on individual threads. More... | |
class | getfem::parallel_boilerplate |
Encapsulates open_mp-related initialization and de-initialization. More... | |
Namespaces | |
getfem | |
GEneric Tool for Finite Element Methods. | |
Macros | |
#define | GETFEM_OMP_PARALLEL(body) body |
Organizes a proper parallel omp section: More... | |
Functions | |
void | getfem::set_num_threads (int n) |
set maximum number of OpenMP threads | |
bool | getfem::me_is_multithreaded_now () |
is the program running in the parallel section | |
bool | getfem::not_multithreaded () |
is the program is running on a single thread | |
size_type | getfem::max_concurrency () |
Maximum number of threads that can run concurrently. | |
Tools for multithreaded, OpenMP and Boost based parallelization.
Definition in file getfem_omp.h.
#define GETFEM_OMP_PARALLEL | ( | body | ) | body |
Organizes a proper parallel omp section:
Definition at line 483 of file getfem_omp.h.