LCI: a Lightweight Communication Interface for Efficient Asynchronous Multithreaded Communication

2025-05-03

AI Summary

To address low asynchronous communication efficiency and coarse-grained resource control in multithreaded environments, this paper introduces LCI (Lightweight Communication Interface), a novel communication library designed for fine-grained multithreading. LCI provides a lightweight API supporting point-to-point primitives and multi-mode completion mechanisms; it features the first thread-efficient runtime built upon atomic data structures and lock-free synchronization—breaking away from traditional MPI-style multiprocess communication paradigms. Furthermore, LCI integrates low-level network optimizations, asynchronous completion queues, and dynamic resource tuning. Experimental evaluation on InfiniBand and Slingshot-11 clusters demonstrates that LCI achieves up to 3.2× higher multithreaded throughput than state-of-the-art communication libraries, even outperforming conventional multiprocess configurations. These advances deliver scalable, high-performance communication support for emerging asynchronous programming models.

Technology Category

• Multiagent Systems: Agent Communication
• Machine Learning: Large Multimodal Models (LMMs)
• Constraint Satisfaction and Optimization: Distributed CSP/Optimization

Application Category

• Security and Privacy: Large-scale security measurements
• Systems and Infrastructure for Web, Mobile and WoT: Data management and stream processing for Web, mobile and wireless applications
• Economics, Online Markets and Human Computation: Cost models of using LLMs in production systems

Abstract

The evolution of architectures, programming models, and algorithms is driving communication towards greater asynchrony and concurrency, usually in multithreaded environments. We present LCI, a communication library designed for efficient asynchronous multithreaded communication. LCI provides a concise interface that supports common point-to-point primitives and diverse completion mechanisms, along with flexible controls for incrementally fine-tuning communication resources and runtime behavior. It features a threading-efficient runtime built on atomic data structures, fine-grained non-blocking locks, and low-level network insights. We evaluate LCI on both Inifiniband and Slingshot-11 clusters with microbenchmarks and two application-level benchmarks. Experiment results show that LCI significantly outperforms existing communication libraries in various multithreaded scenarios, achieving performance that exceeds the traditional multi-process execution mode and unlocking new possibilities for emerging programming models and applications.

Problem

• Efficient asynchronous multithreaded communication in evolving architectures
• Lightweight interface for point-to-point primitives and completion mechanisms
• Optimizing performance in multithreaded scenarios versus traditional methods

Innovation

• Lightweight interface for asynchronous multithreaded communication
• Threading-efficient runtime with atomic data structures
• Flexible controls for fine-tuning communication resources