Comment
Author: Admin | 2025-04-28
C++11 based CORBA implementation MIT Unicomm Asynchronous networking, high-level TCP communication framework uvw A libuv (cross-platform asynchronous I/O) wrapper in C++17 MIT header-only; cmake WNetWrap A WinInet wrapper in C++ MIT wvstreams A C++ networking library including UniConf and a convenient D-Bus API GPL zeromq A fast message queue[edit] Concurrency Library Description License Configuration AdaptiveCpp Provides a SYCL and C++ parallel STL offloading compiler and runtime system for CPUs and GPUs from NVIDIA, AMD, Intel BSD-2-Clause cmake Asyncpp An asynchronous c++ library that provides various concurrent operations MIT cmake BlockingCollection C++11 thread safe, multi-producer, multi-consumer blocking queue, stack & priority queue class GPL-3.0 header-only Boost.Atomic Provides atomic data types and operations on these data types, as well as memory ordering constraints required for coordinating multiple threads through atomic variables. BSL-1.0 Boost.Compute A GPU/parallel-computing library for C++ based on OpenCL. BSL-1.0 cmake Boost.Context A C++11 library that provides a cooperative multitasking abstraction on a single thread. BSL-1.0 Boost.Interprocess Simplifies the use of interprocess communication and synchronization mechanisms and offers a wide range of them: shared memory, memory-mapped files, semaphores, mutexes, condition variables and upgradable mutex types, named versions of the synchronization objects, file locking, message queues. BSL-1.0 Boost.Lockfree Provides non-blocking (aka lock-free) concurrent data structures: a queue, a stack, and a ringbuffer (spsc_queue). BSL-1.0 Boost.MPI A C++-friendly interface to the standard Message Passing Interface BSL-1.0 Boost.Thread Enables the use of multiple threads of execution with shared data and means for synchronizing data between the threads. BSL-1.0 concurrencpp Modern concurrency for C++. Tasks, executors, timers and C++20 coroutines. MIT cmake dispenso High-performance concurrency for C++. parallel_for, Futures, pipelines, timers, timed/periodic tasks, and concurrent data structures. MIT cmake Highway Provides performance-portable, length-agnostic SIMD/vector intrinsics. Supports: SSE3, SSE4, AVX*, NEON, SVE*, WASM SIMD, RISC-V, POWER. (Doc) Apache-2.0 cmake HPX A general purpose C++ runtime system for parallel and distributed applications of any scale (Doc) BSL-1.0 cmake, vcpkg Intel TBB Intel® TBB is a cross-platform C++ library for shared memory parallel programming and heterogeneous computing. The library provides: generic parallel algorithms, concurrent containers, a scalable memory allocator, work-stealing task scheduler, and low-level synchronization primitives. (Src) (Doc) Apache-2.0 or Commercial cmake, make KOKKOS A programming model for writing performance portable HPC applications, using CUDA, HIP, SYCL, HPX, OpenMP and C++ threads as backends (Doc) Custom cmake, make libopenmpi The Open MPI Project is an open-source Message Passing Interface implementation 3-clause BSD libsimdpp A portable zero-overhead C++
Add Comment