2014 · 32 citations · 15 references
EngineeringComputer EngineeringComputer ScienceInterconnection NetworksLow-power DesignSystem-on-chip DesignInterconnect ArchitectureNetwork-on-chip DesignPower ManagementPower-aware DesignRoutingRouting ArchitectureCommunication PatternsDeadlock-free RoutingDistributed Feedback ControlLeakage PowerMulticore ArchitecturesNetwork-on-chip ArchitecturesPower ConsumptionSystem-on-chip Architecture
With the advent of multicore processors and system-on-chip designs, intra-chip communication demands have exacerbated, leading to a growing adoption of scalable networks-on-chip (NoCs) as the interconnect fabric. Today, conventional NoC designs may consume up to 30% of the entire chip's power budget, in large part due to leakage power. In this work, we address this issue by proposing Panthre: our solution deploys power-gating to provide long intervals of uninterrupted sleep to selected units. Packets that would normally use power-gated components are steered away via topology and routing reconfiguration, while Panthre provides low-latency alternate paths to their destinations. The routing reconfiguration operates in a distributed fashion and guarantees that deadlock-free routes are available at all times. At runtime, Panthre adapts to the application's communication patterns by updating its power-gating decisions. It employs a feedback-based distributed mechanism to control the amount of sleeping components and of packets detours, so that performance degradation is kept at a minimum. Our design is flexible, providing a mechanism that designers can use to tradeoff power savings with performance, based on application's requirements. Our experiments on multi-programmed communication-light workloads from the SPEC CPU2006 suite show that Panthre reduces total network power consumption by 14.5% on average, with only a 1.8% degradation in performance, when all processor nodes are active. At times when 15-25% of the processor cores are communication-idle, Panthre enables leakage power savings of 36.9% on average, while still providing connected and deadlock-free routes for all other nodes.
15
A 48-Core IA-32 message-passing processor with DVFS in 45nm CMOS
Jason Howard, Saurabh Dighe, Yatin Hoskote et al. · 2010 · 598 citations
On-Chip Interconnection Architecture of the Tile Processor
David Wentzlaff, Patrick Griffin, Henry Hoffmann et al. · IEEE Micro · 2007 · 574 citations