Coherence in Control: Bridging Many-Core Mapping and Routing through Cost Unification

2026-07-21

AI Summary

This work addresses the critical oversight in existing many-core systems where cache coherence overhead is commonly neglected during task mapping and routing optimization, leading to inaccurate communication modeling and performance bottlenecks. To resolve this, the paper introduces CoCo, a novel framework that, for the first time, integrates cache coherence cost into a unified joint optimization model encompassing task mapping, routing selection, and load balancing. CoCo employs a direction-aware link-weight adaptation mechanism, combining coherence-aware task mapping with a reinforcement learning–based routing algorithm to enable efficient, coordinated decision-making under realistic conditions. Experimental results demonstrate that CoCo significantly outperforms state-of-the-art approaches, reducing link utilization by 88.46%, packet latency by 17.40%, and overall execution time by 17.58%.

Abstract

The rapid growth of data-intensive applications increases communication demands in many-core systems, where cache coherence, while essential for correct communication and data consistency, introduces substantial overhead due to frequent data sharing and coherence activities. As system scale and workload complexity grow, the resulting coherence traffic intensifies communication pressure, making the co-optimization of task mapping and routing essential for improving system performance. However, most existing approaches overlook cache coherence, leaving a substantial portion of coherence-induced communication unaccounted for and creating a mismatch between optimization objectives and actual communication patterns. Furthermore, by employing separate cost evaluators for mapping and routing, these approaches complicate objective coordination, may lead to conflicting decisions, and fail to capture the coherence-induced coupling between the two stages. To address these challenges, we propose CoCo, a coherence-aware co-optimization framework that jointly integrates task mapping and routing under a unified cost model for realistic scenarios. This unified model integrates communication cost, coherence overhead, and load imbalance into a single objective, enabling coherence-aware decision-making and effective trade-offs among optimization goals. Guided by this model, CoCo combines coherence-guided task mapping with reinforcement learning-based routing, where directional link weights are adjusted according to communication behavior to improve traffic distribution, enabling coherence-aware co-optimization for many-core systems. Experimental results show that CoCo reduces link utilization by 88.46%, packet delay by 17.40%, and execution time by 17.58% compared with existing approaches, highlighting the importance of cache coherence in co-optimization design.

Problem

• cache coherence
• many-core systems
• task mapping
• routing
• co-optimization

Innovation

• cache coherence
• co-optimization
• many-core systems
• unified cost model
• reinforcement learning-based routing