Replace ceres::String* with their more modern and performant
absl strings library equivalent and delete our string
manipulation library.
Change-Id: Iecbdba9864e0abf329778f81fdc0708f78f7594f
1. Add abseil-cpp as a submodule. We are tracking the latest LTS
release, which is lts_2024_01_16.
2. Replace glog/gflags with absl::log and absl::flags.
3. Remove miniglog
4. Also take a whack at making the bazel build work with
abseil-cpp and gtest.
There are a number of TODOs in this CL that still need to be resolved.
Change-Id: I39355ed7d61375be4ebcbc8596d9cc70acc1c678
1. Add a version history
2. Update copyright years across the code base
3. Run format_all.sh
4. Update version strings from 2.1.0 to 2.2.0 in the docs and
elsewhere.
Change-Id: I46d8d479d54bd6002d532785e67342106e73c9ac
1. Add threading to all three subclasses of BlockRandomAccessMatrix.
i.e. BlockRandomAccessDenseMatrix, BlockRandomAccessSparseMatrix
and BlockRandomAccessDenseMatrix.
For BlockRandomAccessDenseMatrix and BlockRandomAccessSparseMatrix
this just means SetZero is parallelized. Which by itself is no
big deal, but by doing so, the constructor for all three subclasses
become uniform.
BlockRandomAccessSparseMatrix::SymmetricRightMultiplyAndAccumulate
maybe threaded in the future if needed.
BlockRandomAccessDiagonalMatrix is the biggest beneficiary. SetZero
Invert and RightMultiplyAndAccumulate are all threaded now.
2. Change the storage in BlockRandomAccessDiagonalMatrix from
TripletSparseMatrix to CompressedRowSparseMatrix. This has no
performance implications since we do not really use the capabilities
of the underlying matrix indexing representation. This is a forward
looking change when we decide to transfer this matrix to the GPU,
a CompressedRowSparseMatrix will save on a data conversion.
3. Use std::unique_ptr as needed and eliminate the need for custom
destructors.
4. Modify CompressedRowSparseMatrix::CreateBlockDiagonalMatrix to
take a nullptr as the data vector.
Fixes https://github.com/ceres-solver/ceres-solver/issues/936
Fixes https://github.com/ceres-solver/ceres-solver/issues/935
Change-Id: Ia6487f2d924fbe669835bdcc38abf2b451bda4ee
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
Previously some matrices used Block to keep track of
row/column block sizes and some would just use ints, and
then compute the position of each row and column from it.
By uniformly using Block everywhere, we reduce duplicate
computation and data copies.
I also cleaned up a bunch of c++17 related stuff as I edited
these files.
Change-Id: I4c86b1593fd4c91f9057fbb38314f62f303e0477
Use same instance of a PRNG throughout by passing it to methods and
functions as an argument to generate random numbers without breaking the
sequence.
Change-Id: Ib024bbc1ea2d14e4b9afb71857856a5fb77b1667
These methods were historically poorly named and every time I read code
I get confused whether they are just multiplying or multiplying and
adding. Clarifying them also gives us the changce to introduce
RightMultiply and LeftMultiply methods in the base class which will
simplify a number call sites in a subsequent CL.
Fixes https://github.com/ceres-solver/ceres-solver/issues/855
Change-Id: Ice4fb483f1acd02527a6dd753ef0c5a66037f4b0
1. Remove an unused variable from block_sparse_matrix.cc
2. Add explicit types to the distributions to get around
-Wctad-maybe-unsupported
Change-Id: Ib7d606fbfe2b93ba4fce408f38ee4f7626b74ff0
Currently, the logic for exporting symbols is rather complicated: when
tests are enabled internal symbols are exported in addition to the
public symbols. Such logic causes several problems. (1) Test binaries
link against a Ceres build that is different from the final release
since fewer optimizations are applied if more symbols are exported. (2)
Also, some toolchains hide symbols by default breaking the existing
logic eventually causing linker errors.
Since internal symbols are not intended to be used outside of the
project, we can compile them into object files and use exactly the same
binary code both for the final build and the tests without relying on
conditionals.
By default, all symbols are now hidden unless annotated as public.
Internal symbols are explicitly marked as not being exported in case
users chose not to hide symbols by default.
Change-Id: I589dd10be2f6f438508783cf99d141af0120057b
Applied changes correspond to clang-tidy fixes
stemming from the modernize-use-equals-default check.
Change-Id: I254b0908a76d464131564b637cd0e42a6b03fb5a
- Change formatting standard to Cpp11. Main difference is not having
the space between two closing >> for nested templates. We don't
choose c++14, because older versions of clang-format (version 9
and earlier) don't know this value yet, and it doesn't make a
difference in the formatting.
- Apply clang-format to all (non generated) internal source files.
- Manually fix some code sections (clang-format on/off) and c-strings
- Exclude some embedded external files with very different formatting
(gtest/gmock)
- Add script to format all source files
Change-Id: Ic6cea41575ad6e37c9e136dbce176b0d505dc44d
All three errors are of the form where, the vector storing
the columns array for a CompressedRowSparseMatrix is being
accessed out of bounds. But in each case, the access is innocuous
because there are other tests which prevent it from being used.
However, if one compiles with debug mode on, the bounds checking
in the underlying std::vector triggers an error.
More details:
1. FromTripletSparseMatrix tried accessing the col vector of
a matrix with zero rows, but the following code was a no-op
because there was nothing to copy.
Adding an early return which deals with this case fixes this.
2. RightMultiply and SquaredColumnNorm had the following loop
while (r > cols_[idx] && idx < idx_end) {
++idx;
}
where cols_ was being accessed out of bounds, before idx < idx_end
was being checked. Swapping the order of the comparisons fixes this
error.
@richmattes reported this error.
https://github.com/ceres-solver/ceres-solver/issues/383
Change-Id: I2dbc90ef24ecaffc6f46f1622339d6053b43db45
1. Add Solver::Options::use_mixed_precision_solves,
and Solver::Options::max_num_refinement_iterations.
2. Make SparseCholesky::Create return a unique_ptr.
3. SparseCholesky::Create now takes LinearSolver::Options
as an argument.
4. IterativeRefiner's constructor does not require num_cols
as an argument.
5. SparseNormalCholeskySolver now uses a separate rhs vector.
This basic implementation results in a 10% reduction in solver time
and 30% reduction in linear solver memory usage.
Change-Id: I6830f32cae2febf082d2733262eb2c9f0482b0ea
Even though we added support for storing the upper and
lower triangular parts of symmetric matrices in
CompressedRowSparseMatrix. RightMultiply, LeftMultiply
and SquaredColumnNorm were not modified to account for this.
This CL changes their implementation and adds thorough
tests.
Also methods that cannot work correctly with symmetric
storage now CHECK and fail, because that indicates
programmer error.
Change-Id: I76288472c8bac98db7376a79bdb6259e346ef2b7
Remove outer product computation code from CompressedRowSparseMatrix.
In the process also remove the crsb_cols and crsb_rows vectors from
the matrix, which were added to carry the block sparsity of the matrix
so that the outer product could be computed fast.
InnerProductComputer and its reliance on BlockSparseMatrix has
rendered all of this code moot.
Change-Id: If3ee0dc8ad4ff79594fd1eebc15a647c4495d726
1. Convert a CompressedRowSparseMatrix constructor which
takes a TripletSparseMatrix as input into a factory method
which allows the input to be transposed.
2. Move the random matrix creation routine for CompressedRowSparseMatrix
from being a standalone function to a static method.
3. Add a corresponding random matrix generation static method to
TripletSparseMatrix.
4. Add a new constructor to TripletSparseMatrix, which takes as input
the row, col and values arrays.
Change-Id: Iec7b184646818f432a5e6822bea3b2f3128a82aa
Now that there is a single piece of code doing the outer product
computation for all three sparse linear algebra backends, move
this code one level up the call stack and there by make the actual
per-library solver code shorter and simpler.
Also fix a minor omission in the outer product computation code
where row/column blocks were not being copied over to the
outer product matrix.
Change-Id: I22a7967bdc659385b741901afefa7af312e676e5
SolveLowerTriangularInPlace
SolveLowerTriangularTransposeInPlace
were unused functions which can be removed.
Change-Id: I0fd29c1efae2a0a74666f6e3541473bebc22ae82
By adding an enum to CompressedRowSparseMatrix, which indicates
whether the matrix is unsymmetric, upper or lower triangular
we are able to improve the readability and fix some minor
bugs in the way some matrix manipulation code was being
called.
Thank to William Rucklidge for this suggestion.
Change-Id: I355c90d11cd5d31f5a25741b0bda4fc4583e9095
Move it to compressed_row_sparse_matrix.h/cc for upcoming re-use.
Also clean up the tests for ComputeOuterProduct so that they do
not depend on CXSparse anymore and use Eigen instead. This also
makes the test simpler and shorter.
Change-Id: I06bbeb3b0c6a07fb1f3da354ef0abd17d246be9a
1. Add stype to the outerproduct computation to control the output
matrix in upper or lower triangular matrix. For SuiteSparse,
upper triangular matrix is generated. SuiteSparse can directly use
this matrix format for cholesky without matrix transpose overhead.
2. Change the outerproduct computation to block multiplication. This
reduces the computation complexity for the sort in preprocessing, also
allows formulation of the block outerproduct computation as dense Eigen
block matrix multiplication.
3. Solve 32 Tango problems on Qualcomm MSM8994 Cortex-A53 (1.55GHz)
before change: 140 seconds
after change: 131 seconds
Change-Id: I8054114cef911de6a303310a448821ca296e4744
The test for CompressedRowSparseMatrix::AppendRows tries to add
a matrix of size zero, which results in an invalid pointer deferencing
even though that pointer is never written to.
Change-Id: I97dba37082bd5dad242ae1af0447a9178cd92027
Since Ceres is moving to using GitHub for issues, and the Google
Code URL in the current copyright header will soon become invalid,
update all the headers.
Change-Id: I1fce70375d1bcf098591f07b4d8f01a5c1e0789c
For historical reasons we had a "using namespace std;" in port.h. This
is generally a bad idea. So removing it and along the way doing a bunch
of cpplint cleanup.
Change-Id: Ia125601a55ae62695e247fb0250df4c6f86c46c6
The standard sparse normal Cholesky solver assumes a fixed
sparsity pattern which is useful for a large number of problems
presented to Ceres. However, some problems are symbolically dense
but numerically sparse i.e. each residual is a function of a
large number of parameters but at any given state the residual
only depends on a sparse subset of them. For these class of
problems it is faster to re-analyse the sparsity pattern of the
jacobian at each iteration of the non-linear optimisation instead
of including all of the zero entries in the step computation.
The proposed solution adds the dynamic_sparsity option which can
be used with SPARSE_NORMAL_CHOLESKY. A
DynamicCompressedRowSparseMatrix type (which extends
CompressedRowSparseMatrix) has been introduced which allows
dynamic addition and removal of elements. A Finalize method is
provided which then consolidates the matrix so that it can be
used in place of a regular CompressedRowSparseMatrix. An
associated jacobian writer has also been provided.
Changes that were required to make this extension were adding the
SetMaxNumNonZeros method to CompressedRowSparseMatrix and adding
a JacobianFinalizer template parameter to the ProgramEvaluator.
Change-Id: Ia5a8a9523fdae8d5b027bc35e70b4611ec2a8d01
When using sparse cholesky factorization to solve the linear
least squares problem:
Ax = b
There are two sources of computational complexity.
1. Computing H = A'A
2. Computing the sparse Cholesky factorization of H.
Doing 1. using CX_SPARSE is particularly expensive, as it uses
a generic cs_multiply function which computes the structure of
the matrix H everytime, reallocates memory and does not take
advantage of the fact that the matrix being computed is a symmetric
outer product.
This change adds a custom symmetric outer product algorithm for
CompressedRowSparseMatrix.
It has a symbolic phase, where it computes the sparsity structure
of the output matrix and a "program" which allows the actual
multiplication routine to determine exactly which entry in the
values array each term in the product contributes to.
With these two bits of information, the outer product H = A'A
can be computed extremely fast without any reasoning about
the structure of H.
Further gains in efficiency are made by exploiting the block
structure of A.
With this change, SPARSE_NORMAL_CHOLESKY with CX_SPARSE as the
backend results in > 300% speedup for some problems.
The symbolic analysis phase of the solver is a bit more expensive
now but the increased cost is made up in 3-4 iterations.
Change-Id: I5e4a72b4d03ba41b378a2634330bc22b299c0f12
CompressedRowSparseMatrix can store the row and column block structure
but the AppendRows and DeleteRows methods did not pay attention to them.
This meant that it was possible to get to a CompressedRowSparseMatrix
whose block structure did not match the contents of the matrix.
This change fixes this problem.
Change-Id: I1b3c807fc03d8c049ee20511e2bc62806d211b81
Drop support for protocol buffers.
Add CompressedRowSparseMatrix::CreateBlockDiagonalMatrix.
Add CompressedRowSparseMatrix::SolveLowerTriangularInPlace.
Add CompressedRowSparseMatrix::SolveLowerTriangularTranposeInPlace.
Add CompressedRowSparseMatrix::Transpose.
Change-Id: I2328afca9fac632685eac72ebb00998bd3510187
Sameer Agarwal