forked from OSchip/llvm-project
49 lines
1.4 KiB
ReStructuredText
49 lines
1.4 KiB
ReStructuredText
Rewriting generic-mode kernel with a customized state machine. [OMP131]
|
|
=======================================================================
|
|
|
|
.. _omp131:
|
|
|
|
This optimization remark indicates that a generic-mode kernel on the device was
|
|
specialized for the given target region. When offloading in generic-mode, a
|
|
state machine is required to schedule the work between the parallel worker
|
|
threads. This optimization specializes the state machine in cases where there is
|
|
a known number of parallel regions inside the kernel. A much simpler state
|
|
machine can be used if it is known that there is no nested parallelism and the
|
|
number of regions to schedule is a static amount.
|
|
|
|
Examples
|
|
--------
|
|
|
|
This optimization should occur on any generic-mode kernel that has visibility on
|
|
all parallel regions, but cannot be moved to SPMD-mode and has no nested
|
|
parallelism.
|
|
|
|
.. code-block:: c++
|
|
|
|
#pragma omp declare target
|
|
int TID;
|
|
#pragma omp end declare target
|
|
|
|
void foo() {
|
|
#pragma omp target
|
|
{
|
|
TID = omp_get_thread_num();
|
|
#pragma omp parallel
|
|
{
|
|
work();
|
|
}
|
|
}
|
|
}
|
|
|
|
.. code-block:: console
|
|
|
|
$ clang++ -fopenmp -fopenmp-targets=nvptx64 -O2 -Rpass=openmp-opt omp131.cpp
|
|
omp131.cpp:8:1: remark: Rewriting generic-mode kernel with a customized state machine. [OMP131]
|
|
#pragma omp target
|
|
^
|
|
|
|
Diagnostic Scope
|
|
----------------
|
|
|
|
OpenMP target offloading optimization remark.
|