Files
ceres-solver/internal/ceres/eigen_vector_ops.h
T
Dmitriy Korchemkin b158515089 Parallel operations on vectors
Main focus of this change is to parallelize remaining operations (most of them
are operations on vectors) in code-path utilized with iterative Schur
complement.

Parallelization is handled using lazy evaluation of Eigen expressions.

On linux pc with intel 8176 processor parallelization of vector operations has
the following effect:

Running ./bin/parallel_vector_operations_benchmark
Run on (112 X 3200.32 MHz CPU s)
CPU Caches:
  L1 Data 32 KiB (x56)
  L1 Instruction 32 KiB (x56)
  L2 Unified 1024 KiB (x56)
  L3 Unified 39424 KiB (x2)
Load Average: 3.30, 8.41, 11.82
-----------------------------------
Benchmark                      Time
-----------------------------------
SetZero                 10009532 ns
SetZeroParallel/1       10024139 ns
...
SetZeroParallel/16        877606 ns

Negate                   4978856 ns
NegateParallel/1         5145413 ns
...
NegateParallel/16         721823 ns

Assign                  10731408 ns
AssignParallel/1        10749944 ns
...
AssignParallel/16        1829381 ns

D2X                     15214399 ns
D2XParallel/1           15623245 ns
...
D2XParallel/16           2687060 ns

DivideSqrt               8220050 ns
DivideSqrtParallel/1     9088467 ns
...
DivideSqrtParallel/16     905569 ns

Clamp                    3502010 ns
ClampParallel/1          4507897 ns
...
ClampParallel/16          759576 ns

Norm                     4426782 ns
NormParallel/1           4442805 ns
...
NormParallel/16           430290 ns

Dot                      9023276 ns
DotParallel/1            9031304 ns
...
DotParallel/16           1157267 ns

Axpby                   14608289 ns
AxpbyParallel/1         14570825 ns
...
AxpbyParallel/16         2672220 ns
-----------------------------------

Multi-threading of vector operations in ISC and program evaluation results into
the following improvement:

Running ./bin/evaluation_benchmark
--------------------------------------------------------------------------------------
Benchmark                                                               this   2fd81de
--------------------------------------------------------------------------------------
Residuals<problem-13682-4456117-pre.txt>/1                           4136 ms   4292 ms
Residuals<problem-13682-4456117-pre.txt>/2                           2919 ms   2670 ms
Residuals<problem-13682-4456117-pre.txt>/4                           2065 ms   2198 ms
Residuals<problem-13682-4456117-pre.txt>/8                           1458 ms   1609 ms
Residuals<problem-13682-4456117-pre.txt>/16                          1152 ms   1227 ms

ResidualsAndJacobian<problem-13682-4456117-pre.txt>/1               19759 ms  20084 ms
ResidualsAndJacobian<problem-13682-4456117-pre.txt>/2               10921 ms  10977 ms
ResidualsAndJacobian<problem-13682-4456117-pre.txt>/4                6220 ms   6941 ms
ResidualsAndJacobian<problem-13682-4456117-pre.txt>/8                3490 ms   4398 ms
ResidualsAndJacobian<problem-13682-4456117-pre.txt>/16               2277 ms   3172 ms

Plus<problem-13682-4456117-pre.txt>/1                                 339 ms    322 ms
Plus<problem-13682-4456117-pre.txt>/2                                 220 ms
Plus<problem-13682-4456117-pre.txt>/4                                 128 ms
Plus<problem-13682-4456117-pre.txt>/8                                78.0 ms
Plus<problem-13682-4456117-pre.txt>/16                               49.8 ms

ISCRightMultiplyAndAccumulate<problem-13682-4456117-pre.txt>/1       2434 ms   2478 ms
ISCRightMultiplyAndAccumulate<problem-13682-4456117-pre.txt>/2       2706 ms   2688 ms
ISCRightMultiplyAndAccumulate<problem-13682-4456117-pre.txt>/4       1430 ms   1548 ms
ISCRightMultiplyAndAccumulate<problem-13682-4456117-pre.txt>/8        742 ms    883 ms
ISCRightMultiplyAndAccumulate<problem-13682-4456117-pre.txt>/16       438 ms    555 ms

ISCRightMultiplyAndAccumulateDiag<problem-13682-4456117-pre.txt>/1   2438 ms   2481 ms
ISCRightMultiplyAndAccumulateDiag<problem-13682-4456117-pre.txt>/2   2565 ms   2790 ms
ISCRightMultiplyAndAccumulateDiag<problem-13682-4456117-pre.txt>/4   1434 ms   1551 ms
ISCRightMultiplyAndAccumulateDiag<problem-13682-4456117-pre.txt>/8    765 ms    892 ms
ISCRightMultiplyAndAccumulateDiag<problem-13682-4456117-pre.txt>/16   435 ms    559 ms

JacobianSquaredColumnNorm<problem-13682-4456117-pre.txt>/1           1278 ms
JacobianSquaredColumnNorm<problem-13682-4456117-pre.txt>/2           1555 ms
JacobianSquaredColumnNorm<problem-13682-4456117-pre.txt>/4            833 ms
JacobianSquaredColumnNorm<problem-13682-4456117-pre.txt>/8            459 ms
JacobianSquaredColumnNorm<problem-13682-4456117-pre.txt>/16           250 ms

JacobianScaleColumns<problem-13682-4456117-pre.txt>/1                1468 ms
JacobianScaleColumns<problem-13682-4456117-pre.txt>/2                1871 ms
JacobianScaleColumns<problem-13682-4456117-pre.txt>/4                 957 ms
JacobianScaleColumns<problem-13682-4456117-pre.txt>/8                 528 ms
JacobianScaleColumns<problem-13682-4456117-pre.txt>/16                294 ms

End-to-end improvements with bundle_adjuster invoked with
./bin/bundle_adjuster --num_threads 28 --num_iterations 40 \
                      --linear_solver iterative_schur \
                      --preconditioner jacobi --input
---------------------------------------------
Problem                         this  2fd81de
---------------------------------------------
problem-13682-4456117-pre.txt  508.6    892.7
problem-1778-993923-pre.txt    763.8   1129.9
problem-1723-156502-pre.txt      6.3     14.4
problem-356-226730-pre.txt      76.3    116.2
problem-257-65132-pre.txt       38.6     52.0

Change-Id: Ie31cc5015f13fa479c16ffb5ce48c9b880990d49
2022-12-17 02:52:27 +03:00

97 lines
4.0 KiB
C++

// Ceres Solver - A fast non-linear least squares minimizer
// Copyright 2022 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: sameeragarwal@google.com (Sameer Agarwal)
#ifndef CERES_INTERNAL_EIGEN_VECTOR_OPS_H_
#define CERES_INTERNAL_EIGEN_VECTOR_OPS_H_
#include <numeric>
#include "ceres/internal/eigen.h"
#include "ceres/parallel_for.h"
namespace ceres::internal {
// Blas1 operations on Eigen vectors. These functions are needed as an
// abstraction layer so that we can use different versions of a vector style
// object in the conjugate gradients linear solver.
inline double Norm(const Vector& x, ContextImpl* context, int num_threads) {
std::vector<double> norms(num_threads);
ParallelFor(context,
0,
x.rows(),
num_threads,
[&x, &norms](int thread_id, std::tuple<int, int> range) {
auto [start, end] = range;
norms[thread_id] += x.segment(start, end - start).squaredNorm();
});
return std::sqrt(std::accumulate(norms.begin(), norms.end(), 0.));
}
inline void SetZero(Vector& x, ContextImpl* context, int num_threads) {
ParallelSetZero(context, num_threads, x);
}
inline void Axpby(double a,
const Vector& x,
double b,
const Vector& y,
Vector& z,
ContextImpl* context,
int num_threads) {
ParallelAssign(context, num_threads, z, a * x + b * y);
}
template <typename VectorLikeX, typename VectorLikeY>
inline double Dot(const VectorLikeX& x,
const VectorLikeY& y,
ContextImpl* context,
int num_threads) {
std::vector<double> dots(num_threads);
ParallelFor(context,
0,
x.rows(),
num_threads,
[&x, &y, &dots](int thread_id, std::tuple<int, int> range) {
auto [start, end] = range;
const int block_size = end - start;
const auto& x_block = x.segment(start, block_size);
const auto& y_block = y.segment(start, block_size);
dots[thread_id] += x_block.dot(y_block);
});
return std::accumulate(dots.begin(), dots.end(), 0.);
}
inline void Copy(const Vector& from,
Vector& to,
ContextImpl* context,
int num_threads) {
ParallelAssign(context, num_threads, to, from);
}
} // namespace ceres::internal
#endif // CERES_INTERNAL_EIGEN_VECTOR_OPS_H_