Library for reducing tail latency in RAM reads. Contribute to LaurieWired/tailslayer development by creating an account on GitHub.

Lobsters is a community-driven platform for sharing and discussing links to articles, tutorials, and projects related to technology and programming. Readers can learn about a wide range of topics, from software development and system administration to cybersecurity and artificial intelligence. With user submissions, comments, and voting, Lobsters provides a platform for collaborative learning and knowledge sharing among technology enthusiasts.

Lobsters

Tailslayer is a C++ library that reduces tail latency in RAM reads caused by DRAM refresh stalls. It works by replicating data across multiple independent DRAM channels with uncorrelated refresh schedules, using undocumented channel scrambling offsets compatible with AMD, Intel, and Graviton processors. When a read request arrives, it issues hedged reads across all replicas and uses whichever responds first. The library exposes a template-based HedgedReader API where users provide a signal function (to determine when to read) and a work function (to process the result). It handles address calculation and core pinning internally, acting as a hedged vector with logical indices.

GitHub - LaurieWired/tailslayer: Library for reducing tail latency in RAM reads

<p>Duplicate data in memory? In this economy??</p>
