Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Column Cholesky #1366

Merged
merged 2 commits into from
Jul 26, 2023
Merged

Column Cholesky #1366

merged 2 commits into from
Jul 26, 2023

Conversation

upsj
Copy link
Member

@upsj upsj commented Jul 10, 2023

Pulled out of #1344, this contains only the changes that are required to make Cholesky efficient. The other changes are related to memory ordering semantics and can go into another PR.

@ginkgo-bot ginkgo-bot added reg:testing This is related to testing. mod:cuda This is related to the CUDA module. mod:reference This is related to the reference module. mod:hip This is related to the HIP module. type:factorization This is related to the Factorizations labels Jul 10, 2023
@upsj upsj requested a review from a team July 10, 2023 14:55
@upsj upsj self-assigned this Jul 10, 2023
@upsj upsj added the 1:ST:ready-for-review This PR is ready for review label Jul 10, 2023
GKO_ASSERT_MTX_NEAR(this->combined, this->combined_ref,
r<value_type>::value);
},
false);
Copy link
Member

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

why the following tests does not test the non_spd case?

Copy link
Member

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Is it because the l_factor only stores the sparsity not the factor?

Copy link
Member Author

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

non-spd matrices don't have a Cholesky factorization, I'm only testing the symbolic part for these IIRC.

Comment on lines +354 to +356
lookup_offsets, lookup_storage, lookup_descs, diag_idxs,
transpose_idxs, as_device_type(factors->get_values()), storage,
num_rows);
Copy link
Member

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

the factorize(exec, ...) does not need the forest now.

Copy link
Member

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

another question: does the symbolic still needs the forest?

Copy link
Member Author

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

yes, the symbolic factorization internally uses the elimination forest. The elimination forest might be useful for the numerical factorization as well in the future, but I went with an implementation that doesn't need it, but still gives good performance

Comment on lines +204 to +215
{{2, 0, 0, 0, 0, 0, 0, 0, 0, 0},
{0, 2, 0, 0, 0, 0, 0, 0, 0, 0},
{0.5, 0, 2, 0, 0, 0, 0, 0, 0, 0},
{0, 0, 0, 2, 0, 0, 0, 0, 0, 0},
{0, 0.5, 0, 0, 2, 0, 0, 0, 0, 0},
{0, 0, 0, 0, 0, 2, 0, 0, 0, 0},
{0, 0, 0.5, 0, 0, 1, 2, 0, 0, 0},
{0.5, 0, -0.125, 0, 0, 2, -0.96875, 1.67209402770897, 0, 0},
{0, 0, 0, 0.5, 0.5, 0, 0, 0.598052491922453, 1.7726627476498,
0},
{0, 0.5, 0, 0.5, 0.375, 0, 0, 0.598052491922453,
-0.448571948696326, 1.67346688755653}});
Copy link
Member

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

I assume this solution is from matlab or other tools.
I would not like to compute it by hand.

Copy link
Member Author

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

yes, I tried to make the solution as nice as possible, but at some point I had to give up

Copy link
Member

@thoasm thoasm left a comment

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

LGTM!

@upsj upsj added 1:ST:ready-to-merge This PR is ready to merge. and removed 1:ST:ready-for-review This PR is ready for review labels Jul 22, 2023
@sonarcloud
Copy link

sonarcloud bot commented Jul 26, 2023

Kudos, SonarCloud Quality Gate passed!    Quality Gate passed

Bug A 0 Bugs
Vulnerability A 0 Vulnerabilities
Security Hotspot A 0 Security Hotspots
Code Smell A 0 Code Smells

No Coverage information No Coverage information
0.0% 0.0% Duplication

@codecov
Copy link

codecov bot commented Jul 26, 2023

Codecov Report

Patch coverage: 96.36% and project coverage change: +0.39% 🎉

Comparison is base (24223b4) 90.81% compared to head (db38887) 91.20%.

Additional details and impacted files
@@             Coverage Diff             @@
##           develop    #1366      +/-   ##
===========================================
+ Coverage    90.81%   91.20%   +0.39%     
===========================================
  Files          600      600              
  Lines        50754    50693      -61     
===========================================
+ Hits         46091    46236     +145     
+ Misses        4663     4457     -206     
Files Changed Coverage Δ
reference/test/factorization/cholesky_kernels.cpp 95.97% <96.36%> (+3.66%) ⬆️

... and 5 files with indirect coverage changes

☔ View full report in Codecov by Sentry.
📢 Have feedback on the report? Share it here.

@upsj upsj merged commit 945a4d8 into develop Jul 26, 2023
17 checks passed
@upsj upsj deleted the column_cholesky branch July 26, 2023 07:00
@tcojean tcojean mentioned this pull request Nov 6, 2023
tcojean added a commit that referenced this pull request Nov 10, 2023
Release 1.7.0 to master

The Ginkgo team is proud to announce the new Ginkgo minor release 1.7.0. This release brings new features such as:
- Complete GPU-resident sparse direct solvers feature set and interfaces,
- Improved Cholesky factorization performance,
- A new MC64 reordering,
- Batched iterative solver support with the BiCGSTAB solver with batched Dense and ELL matrix types,
- MPI support for the SYCL backend,
- Improved ParILU(T)/ParIC(T) preconditioner convergence,
and more!

If you face an issue, please first check our [known issues page](https://github.com/ginkgo-project/ginkgo/wiki/Known-Issues) and the [open issues list](https://github.com/ginkgo-project/ginkgo/issues) and if you do not find a solution, feel free to [open a new issue](https://github.com/ginkgo-project/ginkgo/issues/new/choose) or ask a question using the [github discussions](https://github.com/ginkgo-project/ginkgo/discussions).

Supported systems and requirements:
+ For all platforms, CMake 3.16+
+ C++14 compliant compiler
+ Linux and macOS
  + GCC: 5.5+
  + clang: 3.9+
  + Intel compiler: 2019+
  + Apple Clang: 14.0 is tested. Earlier versions might also work.
  + NVHPC: 22.7+
  + Cray Compiler: 14.0.1+
  + CUDA module: CMake 3.18+, and CUDA 10.1+ or NVHPC 22.7+
  + HIP module: ROCm 4.5+
  + DPC++ module: Intel oneAPI 2022.1+ with oneMKL and oneDPL. Set the CXX compiler to `dpcpp` or `icpx`.
  + MPI: standard version 3.1+, ideally GPU Aware, for best performance
+ Windows
  + MinGW: GCC 5.5+
  + Microsoft Visual Studio: VS 2019+
  + CUDA module: CUDA 10.1+, Microsoft Visual Studio
  + OpenMP module: MinGW.

### Version support changes

+ CUDA 9.2 is no longer supported and 10.0 is untested [#1382](#1382)
+ Ginkgo now requires CMake version 3.16 (and 3.18 for CUDA) [#1368](#1368)

### Interface changes

+ `const` Factory parameters can no longer be modified through `with_*` functions, as this breaks const-correctness [#1336](#1336) [#1439](#1439)

### New Deprecations

+ The `device_reset` parameter of CUDA and HIP executors no longer has an effect, and its `allocation_mode` parameters have been deprecated in favor of the `Allocator` interface. [#1315](#1315)
+ The CMake parameter `GINKGO_BUILD_DPCPP` has been deprecated in favor of `GINKGO_BUILD_SYCL`. [#1350](#1350)
+ The `gko::reorder::Rcm` interface has been deprecated in favor of `gko::experimental::reorder::Rcm` based on `Permutation`. [#1418](#1418)
+ The Permutation class' `permute_mask` functionality. [#1415](#1415)
+ Multiple functions with typos (`set_complex_subpsace()`, range functions such as `conj_operaton` etc). [#1348](#1348)

### Summary of previous deprecations
+ `gko::lend()` is not necessary anymore.
+ The classes `RelativeResidualNorm` and `AbsoluteResidualNorm` are deprecated in favor of `ResidualNorm`.
+ The class `AmgxPgm` is deprecated in favor of `Pgm`.
+ Default constructors for the CSR `load_balance` and `automatical` strategies
+ The PolymorphicObject's move-semantic `copy_from` variant
+ The templated `SolverBase` class.
+ The class `MachineTopology` is deprecated in favor of `machine_topology`.
+ Logger constructors and create functions with the `executor` parameter.
+ The virtual, protected, Dense functions `compute_norm1_impl`, `add_scaled_impl`, etc.
+ Logger events for solvers and criterion without the additional `implicit_tau_sq` parameter.
+ The global `gko::solver::default_krylov_dim`, use instead `gko::solver::gmres_default_krylov_dim`.

### Added features

+ Adds a batch::BatchLinOp class that forms a base class for batched linear operators such as batched matrix formats, solver and preconditioners [#1379](#1379)
+ Adds a batch::MultiVector class that enables operations such as dot, norm, scale on batched vectors [#1371](#1371)
+ Adds a batch::Dense matrix format that stores batched dense matrices and provides gemv operations for these dense matrices. [#1413](#1413)
+ Adds a batch::Ell matrix format that stores batched Ell matrices and provides spmv operations for these batched Ell matrices. [#1416](#1416) [#1437](#1437)
+ Add a batch::Bicgstab solver (class, core, and reference kernels) that enables iterative solution of batched linear systems [#1438](#1438).
+ Add device kernels (CUDA, HIP, and DPCPP) for batch::Bicgstab solver. [#1443](#1443).
+ New MC64 reordering algorithm which optimizes the diagonal product or sum of a matrix by permuting the rows, and computes additional scaling factors for equilibriation [#1120](#1120)
+ New interface for (non-symmetric) permutation and scaled permutation of Dense and Csr matrices [#1415](#1415)
+ LU and Cholesky Factorizations can now be separated into their factors [#1432](#1432)
+ New symbolic LU factorization algorithm that is optimized for matrices with an almost-symmetric sparsity pattern [#1445](#1445)
+ Sorting kernels for SparsityCsr on all backends [#1343](#1343)
+ Allow passing pre-generated local solver as factory parameter for the distributed Schwarz preconditioner [#1426](#1426)
+ Add DPCPP kernels for Partition [#1034](#1034), and CSR's `check_diagonal_entries` and `add_scaled_identity` functionality [#1436](#1436)
+ Adds a helper function to create a partition based on either local sizes, or local ranges [#1227](#1227)
+ Add function to compute arithmetic mean of dense and distributed vectors [#1275](#1275)
+ Adds `icpx` compiler supports [#1350](#1350)
+ All backends can be built simultaneously [#1333](#1333)
+ Emits a CMake warning in downstream projects that use different compilers than the installed Ginkgo [#1372](#1372)
+ Reordering algorithms in sparse_blas benchmark [#1354](#1354)
+ Benchmarks gained an `-allocator` parameter to specify device allocators [#1385](#1385)
+ Benchmarks gained an `-input_matrix` parameter that initializes the input JSON based on the filename [#1387](#1387)
+ Benchmark inputs can now be reordered as a preprocessing step [#1408](#1408)


### Improvements

+ Significantly improve Cholesky factorization performance [#1366](#1366)
+ Improve parallel build performance [#1378](#1378)
+ Allow constrained parallel test execution using CTest resources [#1373](#1373)
+ Use arithmetic type more inside mixed precision ELL [#1414](#1414)
+ Most factory parameters of factory type no longer need to be constructed explicitly via `.on(exec)` [#1336](#1336) [#1439](#1439)
+ Improve ParILU(T)/ParIC(T) convergence by using more appropriate atomic operations [#1434](#1434)

### Fixes

+ Fix an over-allocation for OpenMP reductions [#1369](#1369)
+ Fix DPCPP's common-kernel reduction for empty input sizes [#1362](#1362)
+ Fix several typos in the API and documentation [#1348](#1348)
+ Fix inconsistent `Threads` between generations [#1388](#1388)
+ Fix benchmark median condition [#1398](#1398)
+ Fix HIP 5.6.0 compilation [#1411](#1411)
+ Fix missing destruction of rand_generator from cuda/hip [#1417](#1417)
+ Fix PAPI logger destruction order [#1419](#1419)
+ Fix TAU logger compilation [#1422](#1422)
+ Fix relative criterion to not iterate if the residual is already zero [#1079](#1079)
+ Fix memory_order invocations with C++20 changes [#1402](#1402)
+ Fix `check_diagonal_entries_exist` report correctly when only missing diagonal value in the last rows. [#1440](#1440)
+ Fix checking OpenMPI version in cross-compilation settings [#1446](#1446)
+ Fix false-positive deprecation warnings in Ginkgo, especially for the old Rcm (it doesn't emit deprecation warnings anymore as a result but is still considered deprecated) [#1444](#1444)


### Related PR: #1451
tcojean added a commit that referenced this pull request Nov 10, 2023
Release 1.7.0 to develop

The Ginkgo team is proud to announce the new Ginkgo minor release 1.7.0. This release brings new features such as:
- Complete GPU-resident sparse direct solvers feature set and interfaces,
- Improved Cholesky factorization performance,
- A new MC64 reordering,
- Batched iterative solver support with the BiCGSTAB solver with batched Dense and ELL matrix types,
- MPI support for the SYCL backend,
- Improved ParILU(T)/ParIC(T) preconditioner convergence,
and more!

If you face an issue, please first check our [known issues page](https://github.com/ginkgo-project/ginkgo/wiki/Known-Issues) and the [open issues list](https://github.com/ginkgo-project/ginkgo/issues) and if you do not find a solution, feel free to [open a new issue](https://github.com/ginkgo-project/ginkgo/issues/new/choose) or ask a question using the [github discussions](https://github.com/ginkgo-project/ginkgo/discussions).

Supported systems and requirements:
+ For all platforms, CMake 3.16+
+ C++14 compliant compiler
+ Linux and macOS
  + GCC: 5.5+
  + clang: 3.9+
  + Intel compiler: 2019+
  + Apple Clang: 14.0 is tested. Earlier versions might also work.
  + NVHPC: 22.7+
  + Cray Compiler: 14.0.1+
  + CUDA module: CMake 3.18+, and CUDA 10.1+ or NVHPC 22.7+
  + HIP module: ROCm 4.5+
  + DPC++ module: Intel oneAPI 2022.1+ with oneMKL and oneDPL. Set the CXX compiler to `dpcpp` or `icpx`.
  + MPI: standard version 3.1+, ideally GPU Aware, for best performance
+ Windows
  + MinGW: GCC 5.5+
  + Microsoft Visual Studio: VS 2019+
  + CUDA module: CUDA 10.1+, Microsoft Visual Studio
  + OpenMP module: MinGW.

### Version support changes

+ CUDA 9.2 is no longer supported and 10.0 is untested [#1382](#1382)
+ Ginkgo now requires CMake version 3.16 (and 3.18 for CUDA) [#1368](#1368)

### Interface changes

+ `const` Factory parameters can no longer be modified through `with_*` functions, as this breaks const-correctness [#1336](#1336) [#1439](#1439)

### New Deprecations

+ The `device_reset` parameter of CUDA and HIP executors no longer has an effect, and its `allocation_mode` parameters have been deprecated in favor of the `Allocator` interface. [#1315](#1315)
+ The CMake parameter `GINKGO_BUILD_DPCPP` has been deprecated in favor of `GINKGO_BUILD_SYCL`. [#1350](#1350)
+ The `gko::reorder::Rcm` interface has been deprecated in favor of `gko::experimental::reorder::Rcm` based on `Permutation`. [#1418](#1418)
+ The Permutation class' `permute_mask` functionality. [#1415](#1415)
+ Multiple functions with typos (`set_complex_subpsace()`, range functions such as `conj_operaton` etc). [#1348](#1348)

### Summary of previous deprecations
+ `gko::lend()` is not necessary anymore.
+ The classes `RelativeResidualNorm` and `AbsoluteResidualNorm` are deprecated in favor of `ResidualNorm`.
+ The class `AmgxPgm` is deprecated in favor of `Pgm`.
+ Default constructors for the CSR `load_balance` and `automatical` strategies
+ The PolymorphicObject's move-semantic `copy_from` variant
+ The templated `SolverBase` class.
+ The class `MachineTopology` is deprecated in favor of `machine_topology`.
+ Logger constructors and create functions with the `executor` parameter.
+ The virtual, protected, Dense functions `compute_norm1_impl`, `add_scaled_impl`, etc.
+ Logger events for solvers and criterion without the additional `implicit_tau_sq` parameter.
+ The global `gko::solver::default_krylov_dim`, use instead `gko::solver::gmres_default_krylov_dim`.

### Added features

+ Adds a batch::BatchLinOp class that forms a base class for batched linear operators such as batched matrix formats, solver and preconditioners [#1379](#1379)
+ Adds a batch::MultiVector class that enables operations such as dot, norm, scale on batched vectors [#1371](#1371)
+ Adds a batch::Dense matrix format that stores batched dense matrices and provides gemv operations for these dense matrices. [#1413](#1413)
+ Adds a batch::Ell matrix format that stores batched Ell matrices and provides spmv operations for these batched Ell matrices. [#1416](#1416) [#1437](#1437)
+ Add a batch::Bicgstab solver (class, core, and reference kernels) that enables iterative solution of batched linear systems [#1438](#1438).
+ Add device kernels (CUDA, HIP, and DPCPP) for batch::Bicgstab solver. [#1443](#1443).
+ New MC64 reordering algorithm which optimizes the diagonal product or sum of a matrix by permuting the rows, and computes additional scaling factors for equilibriation [#1120](#1120)
+ New interface for (non-symmetric) permutation and scaled permutation of Dense and Csr matrices [#1415](#1415)
+ LU and Cholesky Factorizations can now be separated into their factors [#1432](#1432)
+ New symbolic LU factorization algorithm that is optimized for matrices with an almost-symmetric sparsity pattern [#1445](#1445)
+ Sorting kernels for SparsityCsr on all backends [#1343](#1343)
+ Allow passing pre-generated local solver as factory parameter for the distributed Schwarz preconditioner [#1426](#1426)
+ Add DPCPP kernels for Partition [#1034](#1034), and CSR's `check_diagonal_entries` and `add_scaled_identity` functionality [#1436](#1436)
+ Adds a helper function to create a partition based on either local sizes, or local ranges [#1227](#1227)
+ Add function to compute arithmetic mean of dense and distributed vectors [#1275](#1275)
+ Adds `icpx` compiler supports [#1350](#1350)
+ All backends can be built simultaneously [#1333](#1333)
+ Emits a CMake warning in downstream projects that use different compilers than the installed Ginkgo [#1372](#1372)
+ Reordering algorithms in sparse_blas benchmark [#1354](#1354)
+ Benchmarks gained an `-allocator` parameter to specify device allocators [#1385](#1385)
+ Benchmarks gained an `-input_matrix` parameter that initializes the input JSON based on the filename [#1387](#1387)
+ Benchmark inputs can now be reordered as a preprocessing step [#1408](#1408)


### Improvements

+ Significantly improve Cholesky factorization performance [#1366](#1366)
+ Improve parallel build performance [#1378](#1378)
+ Allow constrained parallel test execution using CTest resources [#1373](#1373)
+ Use arithmetic type more inside mixed precision ELL [#1414](#1414)
+ Most factory parameters of factory type no longer need to be constructed explicitly via `.on(exec)` [#1336](#1336) [#1439](#1439)
+ Improve ParILU(T)/ParIC(T) convergence by using more appropriate atomic operations [#1434](#1434)

### Fixes

+ Fix an over-allocation for OpenMP reductions [#1369](#1369)
+ Fix DPCPP's common-kernel reduction for empty input sizes [#1362](#1362)
+ Fix several typos in the API and documentation [#1348](#1348)
+ Fix inconsistent `Threads` between generations [#1388](#1388)
+ Fix benchmark median condition [#1398](#1398)
+ Fix HIP 5.6.0 compilation [#1411](#1411)
+ Fix missing destruction of rand_generator from cuda/hip [#1417](#1417)
+ Fix PAPI logger destruction order [#1419](#1419)
+ Fix TAU logger compilation [#1422](#1422)
+ Fix relative criterion to not iterate if the residual is already zero [#1079](#1079)
+ Fix memory_order invocations with C++20 changes [#1402](#1402)
+ Fix `check_diagonal_entries_exist` report correctly when only missing diagonal value in the last rows. [#1440](#1440)
+ Fix checking OpenMPI version in cross-compilation settings [#1446](#1446)
+ Fix false-positive deprecation warnings in Ginkgo, especially for the old Rcm (it doesn't emit deprecation warnings anymore as a result but is still considered deprecated) [#1444](#1444)

### Related PR: #1454
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
1:ST:ready-to-merge This PR is ready to merge. mod:cuda This is related to the CUDA module. mod:hip This is related to the HIP module. mod:reference This is related to the reference module. reg:testing This is related to testing. type:factorization This is related to the Factorizations
Projects
None yet
Development

Successfully merging this pull request may close these issues.

None yet

4 participants