Virtual-Link：一种可扩展的多生产者、多消费者跨核通信消息队列架构
Virtual-Link: A Scalable Multi-Producer, Multi-Consumer Message Queue Architecture for Cross-Core Communication
摘要：
随着每个片上系统的处理元件数量的增加，跨核通信越来越成为瓶颈。跨核通信的典型硬件解决方案通常是不灵活的;虽然软件解决方案是灵活的，但它们具有性能扩展限制。一个关键的问题，正如我们将要展示的，是基于软件的消息队列机制中的共享状态。本文提出了虚拟链接（VL），一种新的轻量级通信机制与硬件支持，以促进M：N无锁数据移动。VL将作为许多方法的瓶颈的相干共享状态的量减少到零。VL通过将数据保持在快速路径上（即，在芯片上互连内）。VL在一致性总线上实现PE之间的定向缓存注入（存储），从而减少核到核通信的延迟。VL对于流数据上的细粒度任务特别有效。在具有7个基准测试的完整系统模拟器上进行的评估表明，VL实现了2.09倍于最先进的基于软件的通信机制的加速，同时将内存流量减少了61%。
英文摘要：
Cross-core communication is increasingly a bottleneck as the number of processing elements increase per system-on-chip. Typical hardware solutions to cross-core communication are often inflexible; while software solutions are flexible, they have performance scaling limitations. A key problem, as we will show, is that of shared state in software-based message queue mechanisms. This paper proposes Virtual-Link (VL), a novel light-weight communication mechanism with hardware support to facilitate M:N lock-free data movement. VL reduces the amount of coherent shared state, which is a bottleneck for many approaches, to zero. VL provides further latency benefit by keeping data on the fast path (i.e., within the on-chip interconnect). VL enables directed cache-injection (stashing) between PEs on the coherence bus, reducing the latency for core-to-core communication. VL is particularly effective for fine-grain tasks on streaming data. Evaluation on a full system simulator with 7 benchmarks shows that VL achieves a 2.09x speedup over state-of-the-art software-based communication mechanisms, while reducing memory traffic by 61%.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
