[all-commits] [llvm/llvm-project] 25073a: [OpenMP] Add Two-level Distributed Barrier

[Terry Wilmarth via All-commits]

  Branch: refs/heads/main
  Home:   https://github.com/llvm/llvm-project
  Commit: 25073a4ecfc9b2e3cb76776185e63bfdb094cd98
      https://github.com/llvm/llvm-project/commit/25073a4ecfc9b2e3cb76776185e63bfdb094cd98
  Author: Terry Wilmarth <terry.l.wilmarth at intel.com>
  Date:   2021-06-16 (Wed, 16 Jun 2021)

  Changed paths:
    M openmp/runtime/src/i18n/en_US.txt
    M openmp/runtime/src/kmp.h
    M openmp/runtime/src/kmp_atomic.cpp
    M openmp/runtime/src/kmp_barrier.cpp
    A openmp/runtime/src/kmp_barrier.h
    M openmp/runtime/src/kmp_global.cpp
    M openmp/runtime/src/kmp_os.h
    M openmp/runtime/src/kmp_runtime.cpp
    M openmp/runtime/src/kmp_settings.cpp
    M openmp/runtime/src/kmp_stats.h
    M openmp/runtime/src/kmp_str.cpp
    M openmp/runtime/src/kmp_str.h
    M openmp/runtime/src/kmp_tasking.cpp
    M openmp/runtime/src/kmp_wait_release.cpp
    M openmp/runtime/src/kmp_wait_release.h
    M openmp/runtime/src/z_Linux_util.cpp
    M openmp/runtime/src/z_Windows_NT_util.cpp
    M openmp/runtime/test/barrier/omp_barrier.c

  Log Message:
  -----------
  [OpenMP] Add Two-level Distributed Barrier

Two-level distributed barrier is a new experimental barrier designed
for Intel hardware that has better performance in some cases than the
default hyper barrier.

This barrier is designed to handle fine granularity parallelism where
barriers are used frequently with little compute and memory access
between barriers.  There is no need to use it for codes with few
barriers and large granularity compute, or memory intensive
applications, as little difference will be seen between this barrier
and the default hyper barrier. This barrier is designed to work
optimally with a fixed number of threads, and has a significant setup
time, so should NOT be used in situations where the number of threads
in a team is varied frequently.

The two-level distributed barrier is off by default -- hyper barrier
is used by default. To use this barrier, you must set all barrier
patterns to use this type, because it will not work with other barrier
patterns.  Thus, to turn it on, the following settings are required:

KMP_FORKJOIN_BARRIER_PATTERN=dist,dist
KMP_PLAIN_BARRIER_PATTERN=dist,dist
KMP_REDUCTION_BARRIER_PATTERN=dist,dist

Branching factors (set with KMP_FORKJOIN_BARRIER, KMP_PLAIN_BARRIER,
and KMP_REDUCTION_BARRIER) are ignored by the two-level distributed
barrier.

Differential Revision: https://reviews.llvm.org/D103121