max0x7ba/atomic_queue

Health v2 · maintenance only

Flags: no_releases

Adoption not part of the score

1893 stars · 219 forks observed · 2026-08-28

What it is AI-extracted, prompt v1, taxonomy v1, 2026-08-30, confidence not recorded

A C++14 header-only library providing multiple-producer multiple-consumer lock-free queues built on circular buffers and std::atomic. It is designed to minimize the latency between a producer thread pushing an element and a consumer thread popping it.

Use cases

• pass messages between threads with minimal latency
• replace mutex-protected std::queue in a multithreaded pipeline
• build a low-latency producer-consumer work queue
• implement a lock-free SPSC or MPMC ring buffer
• benchmark queue implementations for throughput and latency
• share data between threads in a high-frequency trading or HFT system

When to choose

• you need the lowest possible inter-thread message passing latency
• you want a lightweight header-only C++14 dependency
• you need MPMC or SPSC queues with bounded capacity and no allocations at runtime
• throughput and latency benchmarks matter for your workload

When to avoid

• you need unbounded queues that grow dynamically
• you require batching or blocking semantics with wait/notify primitives
• your platform lacks std::atomic support or you need C++11 compatibility
• you need cross-process rather than cross-thread communication

Facets

library · maturity stable

concurrency benchmarking developer-tools performance windows cpp cross-platform lock-free queue low-latency ring-buffer multi-producer-multi-consumer header-only atomics algorithms linux macos

Member repositories

For agents

markdown · JSON · MCP: product_card(name="max0x7ba/atomic_queue")