mirror of
https://github.com/ceres-solver/ceres-solver.git
synced 2026-08-30 00:50:37 +08:00
Dmitriy Korchemkin
b1fe603305
Parallel implementations for right-multiply by dense vector for: - Partitioned matrix view - Block-sparse matrix - CRS matrix (non-symmetric only) When coupled with non-interleaving indexes in parallel for, this simple aproach provides a reasonable speedup. For example, in CRS case difference with GPGPU approach reduces closer to memory throughput ratio for high enough core count. ./bin/spmv_benchmark ------------------------------------------------------------------- Benchmark Time ------------------------------------------------------------------- BM_BlockSparseRightMultiplyAndAccumulateBA/1 28.5 ms BM_BlockSparseRightMultiplyAndAccumulateBA/2 15.7 ms BM_BlockSparseRightMultiplyAndAccumulateBA/4 9.01 ms BM_BlockSparseRightMultiplyAndAccumulateBA/8 5.60 ms BM_BlockSparseRightMultiplyAndAccumulateBA/16 3.86 ms BM_BlockSparseRightMultiplyAndAccumulateBA/28 3.84 ms BM_BlockSparseRightMultiplyAndAccumulateUnstructured/1 23.8 ms BM_BlockSparseRightMultiplyAndAccumulateUnstructured/2 15.0 ms BM_BlockSparseRightMultiplyAndAccumulateUnstructured/4 8.01 ms BM_BlockSparseRightMultiplyAndAccumulateUnstructured/8 4.02 ms BM_BlockSparseRightMultiplyAndAccumulateUnstructured/16 2.39 ms BM_BlockSparseRightMultiplyAndAccumulateUnstructured/28 1.68 ms BM_BlockSparseLeftMultiplyAndAccumulateBA 30.7 ms BM_BlockSparseLeftMultiplyAndAccumulateUnstructured 41.5 ms BM_CRSRightMultiplyAndAccumulateBA/1 24.1 ms BM_CRSRightMultiplyAndAccumulateBA/2 13.6 ms BM_CRSRightMultiplyAndAccumulateBA/4 8.70 ms BM_CRSRightMultiplyAndAccumulateBA/8 5.34 ms BM_CRSRightMultiplyAndAccumulateBA/16 3.99 ms BM_CRSRightMultiplyAndAccumulateBA/28 4.00 ms BM_CRSRightMultiplyAndAccumulateUnstructured/1 21.1 ms BM_CRSRightMultiplyAndAccumulateUnstructured/2 10.83 ms BM_CRSRightMultiplyAndAccumulateUnstructured/4 5.88 ms BM_CRSRightMultiplyAndAccumulateUnstructured/8 3.68 ms BM_CRSRightMultiplyAndAccumulateUnstructured/16 2.21 ms BM_CRSRightMultiplyAndAccumulateUnstructured/28 1.71 ms BM_CRSLeftMultiplyAndAccumulateBA 23.6 ms BM_CRSLeftMultiplyAndAccumulateUnstructured 22.5 ms BM_CudaRightMultiplyAndAccumulateBA 0.679 ms BM_CudaRightMultiplyAndAccumulateUnstructured 0.480 ms BM_CudaLeftMultiplyAndAccumulateBA 0.774 ms BM_CudaLeftMultiplyAndAccumulateUnstructured 0.361 ms ./bin/partitioned_matrix_view_benchmark ----------------------------------------------------------------- Benchmark Time ----------------------------------------------------------------- BM_PatitionedViewRightMultiplyAndAccumulateE_Static/1 18.5 ms BM_PatitionedViewRightMultiplyAndAccumulateE_Static/2 10.7 ms BM_PatitionedViewRightMultiplyAndAccumulateE_Static/4 6.34 ms BM_PatitionedViewRightMultiplyAndAccumulateE_Static/8 4.26 ms BM_PatitionedViewRightMultiplyAndAccumulateE_Static/16 3.86 ms BM_PatitionedViewRightMultiplyAndAccumulateE_Static/28 3.75 ms BM_PatitionedViewRightMultiplyAndAccumulateF_Static/1 18.8 ms BM_PatitionedViewRightMultiplyAndAccumulateF_Static/2 11.9 ms BM_PatitionedViewRightMultiplyAndAccumulateF_Static/4 6.94 ms BM_PatitionedViewRightMultiplyAndAccumulateF_Static/8 4.41 ms BM_PatitionedViewRightMultiplyAndAccumulateF_Static/16 3.63 ms BM_PatitionedViewRightMultiplyAndAccumulateF_Static/28 3.86 ms Timings correspond to intel 8176 cpu and 2080ti nvidia gpu, with OpenMP threading backend. Change-Id: Idc07d0563103d057ca3c8412de81a7823fe232af
64 lines
2.7 KiB
C++
64 lines
2.7 KiB
C++
// Ceres Solver - A fast non-linear least squares minimizer
|
|
// Copyright 2015 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)
|
|
|
|
#include "ceres/linear_operator.h"
|
|
|
|
#include <glog/logging.h>
|
|
|
|
namespace ceres::internal {
|
|
|
|
void LinearOperator::RightMultiplyAndAccumulate(const double* x,
|
|
double* y,
|
|
ContextImpl* context,
|
|
int num_threads) const {
|
|
(void)context;
|
|
if (num_threads != 1) {
|
|
VLOG(3) << "Parallel right product is not supported by linear operator "
|
|
"implementation";
|
|
}
|
|
RightMultiplyAndAccumulate(x, y);
|
|
}
|
|
|
|
void LinearOperator::LeftMultiplyAndAccumulate(const double* x,
|
|
double* y,
|
|
ContextImpl* context,
|
|
int num_threads) const {
|
|
(void)context;
|
|
if (num_threads != 1) {
|
|
VLOG(3) << "Parallel left product is not supported by linear operator "
|
|
"implementation";
|
|
}
|
|
LeftMultiplyAndAccumulate(x, y);
|
|
}
|
|
|
|
LinearOperator::~LinearOperator() = default;
|
|
|
|
} // namespace ceres::internal
|