We have released HPX 1.9.0 — a major update to our C++ Standard Library for Concurrency and Parallelism. The HPX parallel algorithms now have been fully adapted to C++23, all existing facilities have been adjusted to conform to this version of the Standard as well. We now can proudly announce full conformance to the C++23 concurrency and parallelism facilities. HPX supports all of the parallel algorithms as specified by C++23. We have been able to significantly improve the performance of some of our algorithms. On top of that we support parallel versions of all range-based algorithms and have added more support for explicit vectorization to our algorithms (using std::experimental::simd). Even more work has been done towards implementing P2300 (std::execution) and keeping the underlying senders/receivers facilities in line with the evolving standardization efforts. We have done a lot of refactoring to improve the consistency of our exposed APIs. Last but not least, we have continued to improve our documentation, please have a look here.
If you have any questions, comments, or exploits to report you can reach us on IRC or Matrix (#ste||ar on libera.chat) or email us at hpx-users. We depend on your input!
HPX is a general-purpose parallel C++ runtime system for applications of any scale. It implements all of the related facilities as defined by the C++20 Standard. As of this writing, HPX provides the only widely available open-source implementation of the new C++17, C++20, and C++23 parallel algorithms, including a full set of parallel range-based algorithms. Additionally, HPX implements functionalities proposed as part of the ongoing C++ standardization process, such as large parts of the features related parallelism and concurrency as specified by the upcoming C++23 Standard, the C++ Concurrency TS, Parallelism TS V2, data-parallel algorithms, executors, and many more. It also extends the existing C++ Standard APIs to the distributed case (e.g., compute clusters) and for heterogeneous systems (e.g., GPUs).
HPX seamlessly enables a new Asynchronous C++ Standard Programming Model that tends to improve the parallel efficiency of our applications and helps reducing complexities usually associated with parallelism and concurrency.