forked from OSchip/llvm-project
43 lines
1.2 KiB
ReStructuredText
43 lines
1.2 KiB
ReStructuredText
.. _omp150:
|
|
|
|
Parallel region merged with parallel region at <location>. [OMP150]
|
|
===================================================================
|
|
|
|
This optimization remark indicates that a parallel region was merged with others
|
|
into a single parallel region. Parallel region merging fuses consecutive
|
|
parallel regions to reduce the team activation overhead of forking and increases
|
|
the scope of possible OpenMP-specific optimizations within merged parallel
|
|
regions. This optimization can also guard sequential code between two parallel
|
|
regions if applicable.
|
|
|
|
Example
|
|
-------
|
|
|
|
This optimization should apply to any compatible and consecutive parallel
|
|
regions. In this case the sequential region between the parallel regions will be
|
|
guarded so it is only executed by a single thread in the new merged region.
|
|
|
|
.. code-block:: c++
|
|
|
|
void foo() {
|
|
#pragma omp parallel
|
|
parallel_work();
|
|
|
|
sequential_work();
|
|
|
|
#pragma omp parallel
|
|
parallel_work();
|
|
}
|
|
|
|
.. code-block:: console
|
|
|
|
$ clang++ -fopenmp -O2 -Rpass=openmp-opt -mllvm -openmp-opt-enable-merging omp150.cpp
|
|
omp150.cpp:2:1: remark: Parallel region merged with parallel region at merge.cpp:7:1. [OMP150]
|
|
#pragma omp parallel
|
|
^
|
|
|
|
Diagnostic Scope
|
|
----------------
|
|
|
|
OpenMP optimization remark.
|