Technology-driven limits on runtime power management algorithms for multiprocessor systems-on-chip

Runtime power management is a critical technique for reducing the energy footprint of digital electronic devices and enabling sustainable computing, since it allows electronic devices to dynamically adapt their power and energy consumption to meet performance requirements. In this article, we consider the case of MultiProcessor Systems-on-Chip (MPSoC) implemented using multiple Voltage and Frequency Islands (VFIs) relying on fine-grained Dynamic Voltage and Frequency Scaling (DVFS) to reduce the system power dissipation. In particular, we present a framework to theoretically analyze the impact of three important technology-driven constraints; (i) reliability-driven upper limits on the maximum supply voltage; (ii) inductive noise-driven constraints on the maximum rate of change of voltage/frequency; and (iii) the impact of manufacturing process variations on the performance of DVFS control for multiple VFI MPSoCs. The proposed analysis is general, in the sense that it is not bound to a specific DVFS control algorithm, but instead focuses on theoretically bounding the performance that any DVFS controller can possibly achieve. Our experimental results on real and synthetic benchmarks show that in the presence of reliability- and temperature-driven constraints on the maximum frequency and maximum frequency increment, any DVFS control algorithm will lose up to 87% performance in terms of the number of steps required to reach a reference steady state. In addition, increasing process variations can lead to up to 60% of fabricated chips being unable to meet the specified DVFS control specifications, irrespective of the DVFS algorithm used. Nonetheless, we note that although conventional DVFS might become less effective with technology scaling, it will continue to play an important role in the context of emerging power management techniques, for example, for massively parallel multiprocessor systems where only a subset of cores can be turned on at any given point of time due to total power constraints.

[1]  Jerome Martin,et al.  MAGALI: A Network-on-Chip based multi-core system-on-chip for MIMO 4G SDR , 2010, 2010 IEEE International Conference on Integrated Circuit Design and Technology.

[2]  Eby G. Friedman,et al.  Scaling trends of on-chip power distribution noise , 2002, IEEE Transactions on Very Large Scale Integration (VLSI) Systems.

[3]  Diana Marculescu,et al.  Sunflower : Full-System, Embedded Microarchitecture Evaluation , 2007, HiPEAC.

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

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

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

[7]  Steven M. Nowick,et al.  ACM Journal on Emerging Technologies in Computing Systems , 2010, TODE.

[8]  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.

[9]  Kai Ma,et al.  Temperature-constrained power control for chip multiprocessors with online model estimation , 2009, ISCA '09.

[10]  Vikram Bhatt,et al.  The GreenDroid Mobile Application Processor: An Architecture for Silicon's Dark Future , 2011, IEEE Micro.

[11]  David Z. Pan,et al.  A Voltage-Frequency Island Aware Energy Optimization Framework for Networks-on-Chip , 2011, IEEE Journal on Emerging and Selected Topics in Circuits and Systems.

[12]  Eby G. Friedman,et al.  Scaling trends of on-chip power distribution noise , 2004 .

[13]  Sriram R. Vangal,et al.  A 2 Tb/s 6$\,\times\,$ 4 Mesh Network for a Single-Chip Cloud Computer With DVFS in 45 nm CMOS , 2011, IEEE Journal of Solid-State Circuits.

[14]  D. Marculescu,et al.  Speed and voltage selection for GALS systems based on voltage/frequency islands , 2005, Proceedings of the ASP-DAC 2005. Asia and South Pacific Design Automation Conference, 2005..

[15]  Meeta Sharma Gupta,et al.  System level analysis of fast, per-core DVFS using on-chip switching regulators , 2008, 2008 IEEE 14th International Symposium on High Performance Computer Architecture.

[16]  Giovanni De Micheli,et al.  Multicore thermal management with model predictive control , 2009, 2009 European Conference on Circuit Theory and Design.

[17]  D. Marculescu,et al.  System-Level Process-Driven Variability Analysis for Single and Multiple Voltage-Frequency Island Systems , 2006, 2006 IEEE/ACM International Conference on Computer Aided Design.

[18]  David Z. Pan,et al.  A voltage-frequency island aware energy optimization framework for networks-on-chip , 2008, ICCAD 2008.

[19]  Yu Cao,et al.  New generation of predictive technology model for sub-45nm design exploration , 2006, 7th International Symposium on Quality Electronic Design (ISQED'06).

[20]  Lawrence T. Pileggi,et al.  Active On-Die Suppression of Power Supply Noise , 2006, IEEE Custom Integrated Circuits Conference 2006.

[21]  Saurabh Dighe,et al.  Within-die variation-aware dynamic-voltage-frequency scaling core mapping and thread hopping for an 80-core processor , 2010, 2010 IEEE International Solid-State Circuits Conference - (ISSCC).

[22]  Fabien Clermidy,et al.  An asynchronous power aware and adaptive NoC based circuit , 2008, 2008 IEEE Symposium on VLSI Circuits.

[23]  Chin-Shung Hsu.  Digital control systems , 1982, Proceedings of the IEEE.

[24]  Alaa R. Alameldeen,et al.  Trading off Cache Capacity for Reliability to Enable Low Voltage Operation , 2008, 2008 International Symposium on Computer Architecture.

[25]  Radu Marculescu,et al.  Custom Feedback control: Enabling truly scalable on-chip power management for MPSoCs , 2010, 2010 ACM/IEEE International Symposium on Low-Power Electronics and Design (ISLPED).