Scalable algorithms for solving linear systems of equations

Overview Repositories Revisions Requests Users Attributes Meta

Scalable algorithms for solving linear systems of equations

The goal of the Scalable Linear Solvers project is to develop scalable algorithms and software for solving large, sparse linear systems of equations on parallel computers. The primary software product is Hypre, a library of high performance preconditioners that features parallel multigrid methods for both structured and unstructured grid problems. The problems of interest arise in the simulation codes being developed at LLNL and elsewhere to study physical phenomena in the defense, environmental, energy, and biological sciences.

Sources inherited from project SUSE:SLE-15-SP3:GA
Download package
Checkout Package
osc -A https://api.opensuse.org checkout SUSE:SLE-15-SP4:GA/hypre && cd $_
Create Badge

Build Results
RPM Lint

Refresh

Source Files

Filename	Size	Changed
Add-library-version.patch	0000000989 989 Bytes	about 3 years ago
_multibuild	0000000455 455 Bytes	over 3 years ago
hypre-2.20.0.tar.gz	0005971556 5.69 MB	about 3 years ago
hypre.changes	0000008354 8.16 KB	about 3 years ago
hypre.spec	0000015295 14.9 KB	about 3 years ago
hypre_Makefile_examples.patch	0000000339 339 Bytes	over 4 years ago

Latest Revision

Gustavo Yokoyama Ribeiro (gyribeiro) committed about 3 years ago (revision 2)

- Make cmake files installation non-conflicting.

- Fix hypre package conflicts for non HPC packages.

- Change 'Requires:' to other HPC packages to %requires_eq to depend
  on the exact version. This should take care of HPC packages ignoring
  proper ABI versioning.

- Update to 2.20.0
  * New matrix-based interpolation routines for AMG (CPU and GPU)
  * Added GPU support for aggressive coarsening in AMG
  * New AMG-DD solver
  * Improved distributed sparse matrix-matrix and triple-matrix product
    performance on GPUs
  * IJMatrix/Vector assembly on GPUs (with pointers to GPU memory)
  * Updated caliper usage
  * Separated C and C++ headers
  * Updated to support superlu-dist version to 6.3.1
  * Moved reference manual API to online documentation
  * New AMG features to keep specified F-points and/or C-points.
  * Added GPU support for AMG setup and several interpolation approaches.
  * New parallel ILU solvers and smoothers.
  * New MGR features.
  * Added several interpolation routines based on matrix-matrix interpolations.
  * Various bug fixes.
- Remove patch merged by upstream
  * Fix-empty-elseif-in-CMakeLists.txt.patch
- Rework patch following upstream changes
  * Fix-library-version-numbering.patch Patch removed
  * Add-library-version.patch Patch added

Places