Custom Feedback control: Enabling truly scalable on-chip power management for MPSoCs

In this paper, we propose Custom Feedback Control, a new dynamic voltage and frequency control architecture for MP-SoC designs that bridges the gap between the two extreme points on the performance versus implementation cost tradeoff curve, i.e., fully-centralized and full-decentralized control architectures. We outline a methodology to efficiently explore the vast design space of Custom Feedback control architectures, enabling designers to synthesize controllers that meet both the performance and implementation cost criteria. Our experimental results on an MPSoC platform running a video-encoding application demonstrate that, for the same energy dissipation, Custom Feedback control can achieve within 5% of the performance of a fully-centralized controller with only 17% of the implementation cost. In contrast, the performance of a fully-decentralized controller can be up to 2.5X worse than that of the fully-centralized controller.

[1]  Margaret Martonosi,et al.  Formal online methods for voltage/frequency control in multiple clock domain microprocessors , 2004, ASPLOS XI.

[2]  Jörg Henkel,et al.  TAPE: thermal-aware agent-based power economy for multi/many-core architectures , 2009, ICCAD '09.

[3]  Katsuhiko Ogata,et al.  Discrete-time control systems , 1987 .

[4]  Sander Stuijk,et al.  Exploring trade-offs in buffer requirements and throughput constraints for synchronous dataflow graphs , 2006, 2006 43rd ACM/IEEE Design Automation Conference.

[5]  T. Mohsenin,et al.  A 167-processor 65 nm computational platform with per-processor dynamic supply voltage and dynamic clock frequency scaling , 2008, 2008 IEEE Symposium on VLSI Circuits.

[6]  Radu Marculescu,et al.  Voltage-Frequency Island Partitioning for GALS-based Networks-on-Chip , 2007, 2007 44th ACM/IEEE Design Automation Conference.

[7]  Giovanni De Micheli,et al.  A control theory approach for thermal balancing of MPSoC , 2009, 2009 Asia and South Pacific Design Automation Conference.

[8]  Saurabh Dighe,et al.  Teraflops prototype processor with 80 cores , 2007, 2007 IEEE Hot Chips 19 Symposium (HCS).

[9]  Luca Benini,et al.  A control theoretic approach to energy-efficient pipelined computation in MPSoCs , 2007, TECS.

[10]  Radu Marculescu,et al.  Variation-adaptive feedback control for networks-on-chip with multiple clock domains , 2008, 2008 45th ACM/IEEE Design Automation Conference.

[11]  Luca Benini,et al.  Temperature Control of High-Performance Multi-core Platforms Using Convex Optimization , 2008, 2008 Design, Automation and Test in Europe.