Co is proposed, a coherence-aware co-optimization framework that jointly integrates task mapping and routing under a unified cost model for realistic scenarios, enabling coherence-aware decision-making and effective trade-offs among optimization goals.
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.
Cache coherence is essential for communication in many-core Network-on-Chip (NoC)-based systems. As application scale and complexity increase, efficiently managing communication becomes increasingly challenging, making task mapping a key optimization technique. However, existing task mapping approaches suffer from two major limitations. First, they rely on predefined task graphs whose dependencies are typically derived from program structure or runtime information, such as dataflow, synchronization, traces, or profiling, without explicitly capturing coherence-induced interactions arising from shared data accesses. Consequently, these graphs provide only a partial representation of inter-task relationships, limiting mapping effectiveness. Second, they generally overlook cache coherence, even though coherence traffic constitutes a significant portion of NoC communication. This mismatch between modeled communication behavior and actual runtime interactions often leads to suboptimal mappings and degraded system performance. To address these limitations, we propose CoTM, a coherence-aware task mapping framework that constructs task graphs by inferring inter-task dependencies from dynamic coherence behavior. CoTM employs a lightweight heuristic with a multi-start optimization strategy to iteratively refine task placement, guided by a coherence-aware penalty function that jointly considers coherence traffic and NoC performance metrics. Experimental results demonstrate that CoTM reduces average link utilization by up to 47.85% and total energy consumption by up to 10.30% compared with existing approaches. These results highlight the importance of incorporating cache coherence into task mapping and demonstrate the potential of coherence-aware optimization for future many-core NoC systems.
The proposed Multi-Path Multi-Level Feedback Queueing (MP-MLFQ) leverages the spatial diversity and regularity of DCNs to realize a scheduler with numerous logical priority levels while occupying as low as 2 physical priority queues within network switches.
Alessandro Cornacchia, Andrea Bianco, Paolo Giaccone et al.· 0 citations
The results show that soft SLO limits reduce corrective rescheduling actions by 49% compared to hard-limit approaches while maintaining acceptable performance guarantees, and resource-aware scheduling decreases node-level congestion and further mitigates SLO violations, demonstrating the effectiveness of incorporating application-level flexibility and hardware-level insights into scheduling and rescheduling decisions.
Oliver Larsson, Thijs Metsch, Cristian Klein et al.· 0 citations
Compute and memory resources in cloud environments are strictly managed and isolated by the control plane; in contrast, network resources lack equivalent management and isolation mechanisms. This best-effort treatment of networking leads to significant challenges for modern AI workloads, which have diverse and bandwidth-intensive communication patterns. Without fine-grained network resource control, these workloads suffer from interference, unpredictable throughput, and suboptimal cluster utilization. To address these issues, this paper demonstrates how network bandwidth can be elevated to a first-class, schedulable, and enforceable resource within Kubernetes, the de facto standard for cloud-native orchestration. We introduce a new scheduling capability that models network interfaces as allocatable resources and regulates bandwidth sharing through the Dynamic Resource Allocation (DRA) framework, with enforcement implemented using the Hierarchical Token Bucket (HTB) mechanism. We evaluate the system using multitenant AI workloads derived from real-world communication characteristics with a simulation-based approach and validate the proposed enforcement strategy in a real cluster. Results show that the proposed two-level bandwidth allocation improves tenant performance predictability and satisfaction while maintaining packed cluster utilization.
ReTri, a bidirectional All-to-All schedule for ORNs based on the Trivance algorithm is presented, a bidirectional All-to-All schedule for ORNs based on the Trivance algorithm that improves completion time and improves reconfigurable Bruck by up to 2.1×.
Anton Juerss, Stefan Schmid· Proceedings of the ACM SIGCO...· 0 citations
HyLink is introduced, a two-layer collective communication framework, including a PCIe CCL module and a Multipath Orchestrator module that provides a CPU-driven Domain-Specific Language (DSL) for multi-stage data flows and an auto-pipelined transfer engine for host-side routing and SIMD-accelerated reduction.
Yue Liu, Menghao Zhang, Xuebin Song et al.· Asia-Pacific Workshop on Net...· 0 citations