|
1 | 1 | # Change Log |
2 | 2 | All notable changes to HiOp are documented in this file. |
3 | 3 |
|
| 4 | +## Version 0.7.2: Execution spaces abstractions and misc fixes |
| 5 | +This release hosts a series of comprehensive internal developments and software re-engineering to improve the portability and performance on accelerators/GPU platforms. No changes to the user interface permeated under this release. |
| 6 | + |
| 7 | +### Notable new features |
| 8 | + |
| 9 | +A new execution space abstraction is introduced to allow multiple hardware backends to run concurrently. The proposed design differentiates between "memory backend" and "execution policies" to allow using RAJA with Umpire-managed memory, RAJA with Cuda- or Hip-managed memory, RAJA with std memory, Cuda/Hip kernels with Cuda-/Hip- or Umpire-managed memory, etc. |
| 10 | + |
| 11 | +* Execution spaces: support for memory backends and execution policies by @cnpetra in https://github.com/LLNL/hiop/pull/543 |
| 12 | +* Build: Cuda without raja by @cnpetra in https://github.com/LLNL/hiop/pull/579 |
| 13 | +* Update of RAJA-based dense matrix to support runtime execution spaces by @cnpetra in https://github.com/LLNL/hiop/pull/580 |
| 14 | +* Reorganization of device namespace by @cnpetra in https://github.com/LLNL/hiop/pull/582 |
| 15 | +* RAJA Vector int with ExecSpace by @cnpetra in https://github.com/LLNL/hiop/pull/583 |
| 16 | +* Instrumentation of host vectors with execution spaces by @cnpetra in https://github.com/LLNL/hiop/pull/584 |
| 17 | +* Remove copy from/to device methods in vector classes by @cnpetra in https://github.com/LLNL/hiop/pull/587 |
| 18 | +* Add support for Raja with OpenMP into LLNL CI by @nychiang in https://github.com/LLNL/hiop/pull/566 |
| 19 | + |
| 20 | +New vector classes using vendor-provided API were introduced and documentation was updated/improved |
| 21 | +* Development of `hiopVectorCuda` by @nychiang in https://github.com/LLNL/hiop/pull/572 |
| 22 | +* Implementation of `hiopVectorHip` by @nychiang in https://github.com/LLNL/hiop/pull/590 |
| 23 | +* Update user manual by @nychiang in https://github.com/LLNL/hiop/pull/591 |
| 24 | +* Update the code comments in `hiopVector` classes by @nychiang in https://github.com/LLNL/hiop/pull/592 |
| 25 | + |
| 26 | +Refinement of triangular solver implementation for Ginkgo by @fritzgoebel in https://github.com/LLNL/hiop/pull/585 |
| 27 | + |
| 28 | +### Bug fixes |
| 29 | +* Refine the computation in normal equation system by @nychiang in https://github.com/LLNL/hiop/pull/530 |
| 30 | +* Fix static culibos issue #567 by @nychiang in https://github.com/LLNL/hiop/pull/568 |
| 31 | +* Fix segfault, remove nonsymmetric ginkgo solver by @fritzgoebel in https://github.com/LLNL/hiop/pull/548 |
| 32 | +* Calculate the inverse objective scale correctly. by @tepperly in https://github.com/LLNL/hiop/pull/570 |
| 33 | +* Fix `hiopVectorRajaPar::copyToStartingAt_w_pattern` by @nychiang in https://github.com/LLNL/hiop/pull/569 |
| 34 | +* Gitlab pipeline refactor by @CameronRutherford in https://github.com/LLNL/hiop/pull/597 |
| 35 | + |
| 36 | +### New Contributors |
| 37 | +* @tepperly made their first contribution in https://github.com/LLNL/hiop/pull/570 |
| 38 | + |
| 39 | +**Full Changelog**: https://github.com/LLNL/hiop/compare/v0.7.1...v0.7.2 |
| 40 | + |
4 | 41 | ## Version 0.7.1: Miscellaneous fixes to build system |
5 | 42 | This minor release fixes a couple of issues found in the build system after the major release 0.7 of HiOp. |
6 | 43 |
|
|
0 commit comments