Tardis 2.0: Optimized Time Traveling Coherence for Relaxed Consistency Models

TL;DR

Tardis 2.0 enhances the original cache coherence protocol by supporting relaxed memory models like TSO, PSO, and RC, reducing traffic and improving scalability in shared memory systems.

Contribution

This paper extends Tardis to support multiple relaxed memory models and introduces optimizations for leasing policies and spinning, making it more practical and scalable.

Findings

Improves performance, storage, and network traffic over directory protocols

Supports TSO, PSO, and RC memory models with formal proofs

Simplifies implementation while enhancing scalability

Abstract

Cache coherence scalability is a big challenge in shared memory systems. Traditional protocols do not scale due to the storage and traffic overhead of cache invalidation. Tardis, a recently proposed coherence protocol, removes cache invalidation using logical timestamps and achieves excellent scalability. The original Tardis protocol, however, only supports the Sequential Consistency (SC) memory model, limiting its applicability. Tardis also incurs extra network traffic on some benchmarks due to renew messages, and has suboptimal performance when the program uses spinning to communicate between threads. In this paper, we address these downsides of Tardis protocol and make it significantly more practical. Specifically, we discuss the architectural, memory system and protocol changes required in order to implement the TSO consistency model on Tardis, and prove that the modified protocol satisfies TSO. We also describe modifications for Partial Store Order (PSO) and Release Consistency (RC). Finally, we propose optimizations for better leasing policies and to handle program spinning. On a set of benchmarks, optimized Tardis improves on a full-map directory protocol in the metrics of performance, storage and network traffic, while being simpler to implement.