Changelog for
tbb-devel-2021.13.0-91.2.x86_64.rpm :
* Wed Sep 25 2024 Alessandro de Oliveira Faria
- Update to version 2021.13.0:
* Extended the parallel_reduce and parallel_deterministic_reduce functional form APIs to better support rvalues reduction (GitHub
* #1299).
* Removed use-FORTIFY_SOURCE-from-distribution patch, because of MATCHES \"_FORTIFY_SOURCE\" condition on line 75
* Fri Apr 19 2024 Alessandro de Oliveira Faria - Update to version 2021.12.0:
* Fixed parallel_for_each algorithm behavior for iterators defining iterator_concept trait instead of iterator_category.
* Fixed the incorrect binary search order in TBBConfig.cmake.
* Thu Jan 25 2024 Ana Guerrero - Fix build to handle changes in (open)SUSE specific cmake macros, no user visible changes
* Fri Dec 01 2023 Atri Bhattacharya - Update to version 2021.11.0:
* Fixed tbb::this_task_arena() behavior for specific tbb::task_arena{1,0}.
* Restored performance on the high-core count systems that support _tpause.- Refresh patches to apply cleanly:
* use-FORTIFY_SOURCE-from-distribution.patch
* add-cmake-check-for-libatomic-requirement-when-build.patch- Update Summary and description tags to be consistent with upstream\'s TBB -> oneTBB renaming.
* Thu Nov 23 2023 Bernhard Wiedemann - Avoid stuck build/tests
* Tue Aug 01 2023 Martin Liška
* Add use-FORTIFY_SOURCE-from-distribution.patch and use FS settings from distribution (we use either =2 or =3).
* Tue Aug 01 2023 Alessandro de Oliveira Faria - Update to 2021.10.0:
* Since C++17, parallel algorithms and Flow Graph nodes are allowed to accept pointers to the member functions and member objects as the user-provided callables.
* Added missed member functions, such as assignment operators and swap function, to the concurrent_queue and concurrent_bounded_queue containers.
* Thu Jun 15 2023 Paolo Stivanin - Update to 2021.9.0:
* Hybrid CPU support is now a fully supported feature.
* Fixed the issue reported by the Address Sanitizer.
* Fixed the input_type alias exposed by flow_graph::join_node.- Drop 917.patch (patch was upstreamed).- Drop retry-pthread_create.patch (upstream fixed it by using a similar approach).
* Wed Jan 04 2023 John Paul Adrian Glaubitz - Update to v2021.8.0
* Fixed oneapi::tbb::concurrent_bounded_queue::pop return type (GitHub
* #807).
* Fixed oneapi::tbb::concurrent_queue and oneapi::tbb::concurrent_bounded_queue with non-default constructible value types (GitHub
* #885).
* Fixed incorrect splitting of iteration space in case there is no support for proportional splitting in custom ranges.- Add patch to link against libatomic where necessary
* add-cmake-check-for-libatomic-requirement-when-build.patch- Drop 5cb212d44732947396abdd39eae1229c7cd51644.patch, merged upstream- Use correct changelog entries for v2021.7.0
* Sun Dec 11 2022 Dirk Müller - update to v2021.7.0:
* Memory allocator crash when allocating ~1TB on 64-bit systems (GitHub
* #838).
* Thread Distribution over NUMA Nodes on Windows OS systems.
* For oneapi::tbb::suspend it is now guaranteed that the user-specified callable object is executed by the calling thread.
* Sat Sep 24 2022 Dirk Müller - update to 2021.6.0:
* Improved support and use of the latest C++ standards for parallel_sort that allows using this algorithm with user-defined and standard library-defined objects with modern semantics.
* The following features are now fully functional: task_arena extensions, collaborative_call_once, adaptive mutexes, heterogeneous overloads for concurrent_hash_map, and task_scheduler_handle.
* Added support for Windows
* Server 2022 and Python 3.10.
* Memory allocator crash on a system with an incomplete /proc/meminfo
* Incorrect blocking of task stealing
* Hang due to incorrect decrement of a limiter_node
* Memory corruption in some rare cases when passing big messages in a flow graph
* Possible deadlock in a throwable flow graph node with a lightweight policy. The lightweight policy is now ignored for functors that can throw exceptions
* Crash when obtaining a range from empty ordered and unordered containers
* Deadlock in a concurrent_vector resize() that could happen when the new size is less than the previous size- drop tbb-pr609-32bit-mwaitpkg.patch (upstream)- add 5cb212d44732947396abdd39eae1229c7cd51644.patch, 917.patch: build on riscv64, hppa, s390x
* Fri Aug 05 2022 Martin Liška - Add retry-pthread_create.patch that fixes gh#oneapi-src/oneTBB#824.
* Sat May 07 2022 Dirk Müller - update to 2021.1.5:
* Reworked synchronization mechanism to reduce contention when multiple task_arena’s are used concurrently.
* Fixed sporadic memory corruption.
* Enabled Microsoft Visual Studio
* 2022 and Python 3.9 support.
* Extended task_group interface with a new run_and_wait overload to accept task_handle.
* Fixed possible correctness issue in queuing_rw_mutex on non-Intel platforms.
* Fixed sporadic memory corruption.
* Tue Apr 05 2022 Atri Bhattacharya - For 32-bit systems, rename tbb32.pc (default upstream for 32-bit) to tbb.pc (same as 64-bit) so that applications depending on tbb do not have to call different pkgconfig modules based on arch.
* Fri Oct 08 2021 Ben Greiner - Allow gcc11- Add tbb-pr609-32bit-mwaitpkg.patch gh#oneapi-src/oneTBB#609
* fixes 32-bit build with gcc11- Only run ctest when --with test is given
* Tue Oct 05 2021 Ben Greiner - Update to version 2021.4
* Large release notes since 2020.3: https://software.intel.com/content/www/us/en/develop/articles/intel-oneapi-threading-building-blocks-release-notes.html- Drop python2 package- Drop patches:
* disable-irml.patch -- install the library
* optflags.patch -- build system change
* reproducible.patch -- build system change- Refresh cmake-remove-include-path.patch- Add libirml subpackage for python module- Add libtbbbind library package for NUMA support