Files
ceres-solver/internal/ceres/parallel_for_openmp.cc
T
Mike Vitus 5d8b494557 Adds a ParallelFor wrapper for no threads and OpenMP.
With the addition of C++11 support we can simplify the parallel for code by
removing the ifdef branching.  Converts coordinate_descent_minimizer.cc to use
the thread_id ParallelFor API.

Tested by building with OpenMP, C++11 threads, TBB, and no threads.  All tests
pass.

Also compared timing via the bundle adjuster.

./bin/bundle_adjuster --input=../problem-744-543562-pre.txt

With OpenMP num_threads=8

Head:
Time (in seconds):
  Residual only evaluation           0.807753 (5)
  Jacobian & residual evaluation     4.489404 (6)
  Linear solver                     41.826481 (5)
Minimizer                           50.745857
Total                               73.294424

CL:
Time (in seconds):
  Residual only evaluation           0.970483 (5)
  Jacobian & residual evaluation     4.647438 (6)
  Linear solver                     41.781892 (5)
Minimizer                           50.848904
Total                               73.089983

With OpenMP num_threads=1

HEAD:
Time (in seconds):
  Residual only evaluation           2.990246 (5)
  Jacobian & residual evaluation    14.132090 (6)
  Linear solver                     79.631951 (5)
Minimizer                          100.281847
Total                              122.946267

CL:
Time (in seconds):
  Residual only evaluation           3.075178 (5)
  Jacobian & residual evaluation    13.966451 (6)
  Linear solver                     77.005441 (5)
Minimizer                           97.568712
Total                              120.410454

Change-Id: I1857d7943073be7465b6c6476bf46ab11c5475a3
2018-04-09 10:10:03 -07:00

84 lines
3.1 KiB
C++

// Ceres Solver - A fast non-linear least squares minimizer
// Copyright 2018 Google Inc. All rights reserved.
// http://ceres-solver.org/
//
// Redistribution and use in source and binary forms, with or without
// modification, are permitted provided that the following conditions are met:
//
// * Redistributions of source code must retain the above copyright notice,
// this list of conditions and the following disclaimer.
// * Redistributions in binary form must reproduce the above copyright notice,
// this list of conditions and the following disclaimer in the documentation
// and/or other materials provided with the distribution.
// * Neither the name of Google Inc. nor the names of its contributors may be
// used to endorse or promote products derived from this software without
// specific prior written permission.
//
// THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS "AS IS"
// AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE
// IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE
// ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT OWNER OR CONTRIBUTORS BE
// LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR
// CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF
// SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS
// INTERRUPTION) HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN
// CONTRACT, STRICT LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE)
// ARISING IN ANY WAY OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE
// POSSIBILITY OF SUCH DAMAGE.
//
// Author: vitus@google.com (Michael Vitus)
// This include must come before any #ifndef check on Ceres compile options.
#include "ceres/internal/port.h"
#if !(defined(CERES_USE_TBB) || defined(CERES_USE_CXX11_THREADS))
#include "ceres/parallel_for.h"
#include "ceres/scoped_thread_token.h"
#include "ceres/thread_token_provider.h"
#include "glog/logging.h"
namespace ceres {
namespace internal {
void ParallelFor(ContextImpl* context,
int start,
int end,
int num_threads,
const std::function<void(int)>& function) {
CHECK_GT(num_threads, 0);
CHECK(context != NULL);
if (end <= start) {
return;
}
#ifdef CERES_USE_OPENMP
#pragma omp parallel for num_threads(num_threads) \
schedule(dynamic) if (num_threads > 1)
#endif // CERES_USE_OPENMP
for (int i = start; i < end; ++i) {
function(i);
}
}
void ParallelFor(ContextImpl* context,
int start,
int end,
int num_threads,
const std::function<void(int thread_id, int i)>& function) {
CHECK(context != NULL);
ThreadTokenProvider thread_token_provider(num_threads);
ParallelFor(context, start, end, num_threads, [&](int i) {
const ScopedThreadToken scoped_thread_token(&thread_token_provider);
const int thread_id = scoped_thread_token.token();
function(thread_id, i);
});
}
} // namespace internal
} // namespace ceres
#endif // !(defined(CERES_USE_TBB) || defined(CERES_USE_CXX11_THREADS))