Interplay of Power Management at Core and Server Level

While the feature sizes of recent Complementary Metal
Oxid Semiconductor (CMOS) devices decrease the influence of static
power prevails their energy consumption. Thus, power savings that
benefit from Dynamic Frequency and Voltage Scaling (DVFS) are
diminishing and temporal shutdown of cores or other microchip
components become more worthwhile. A consequence of powering off unused parts of a chip is that the
relative difference between idle and fully loaded power consumption
is increased. That means, future chips and whole server systems gain
more power saving potential through power-aware load balancing,
whereas in former times this power saving approach had only
limited effect, and thus, was not widely adopted. While powering
off complete servers was used to save energy, it will be superfluous
in many cases when cores can be powered down. An important
advantage that comes with that is a largely reduced time to respond
to increased computational demand. We include the above developments in a server power model
and quantify the advantage. Our conclusion is that strategies from
datacenters when to power off server systems might be used in the
future on core level, while load balancing mechanisms previously
used at core level might be used in the future at server level.

Authors:

• Jörg Lenhardt
• Wolfram Schiffmann
• Jörg Keller

Keywords:

• Power efficiency
• static power consumption
• dynamic power consumption
• CMOS.

References:

[1] M. B. Taylor. A Landscape of the New Dark Silicon Design Regime.
IEEE Micro, 33(5):8–19, 2013.
[2] R. Sch¨one, D. Molka, and M. Werner. Wake-up latencies for processor
idle states on current x86 processors. Computer Science - Research and
Development, pages 1–9, 2014.
[3] Standard Performance Evaluation Corporation. All Published
SPECpower ssj2008 Results, https://www.spec.org/power ssj2008/
results/power ssj2008.html, 2015.
[4] L. A. Barroso and U. H¨olzle. The case for energy-proportional
computing. Computer, 40(12):33–37, 2007.
[5] J. Srinivasan. An overview of static power dissipation. Technical report,
Internal report.
[6] E. L. Sueur and G. Heiser. Dynamic voltage and frequency scaling: the
laws of diminishing returns. In Int. Conf. on Power Aware Computing
and Systems, HotPower’10, pages 1–8. USENIX Association, 2010.
[7] A. Carroll and G. Heiser. Unifying DVFS and Offlining in Mobile
Multicores. In IEEE Real Time and Application Systems (RTAS) 2014,
Berlin, 2014.
[8] A. Dhingra and S. Paul. A Survey of Energy Efficient Data Centres in
a Cloud Computing Environment. IJARCCE, 2(10):4033–4040, 2013.
[9] J. Leverich, M. Monchiero, V. Talwar, P. Ranganathan, and C. Kozyrakis.
Power Management of Datacenter Workloads Using Per-Core Power
Gating. IEEE Computer Architecture Letters, 8(2):48–51, February
2009. [10] L. Wang and K. Skadron. Implications of the Power Wall: Dim Cores
and Reconfigurable Logic. IEEE Micro, (September/October):40–48,
2013.
[11] G. Da Costa. Heterogeneity: The Key to Achieve Power-Proportional
Computing. 13th Symp. on Cluster, Cloud, and Grid Computing, pages
656–662, May 2013.
[12] R. H. Dennard, F. H. Gaensslen, Y. Hwa-Nien, V.L. Rideout, E. Bassous,
and A. LeBlanc. Design of Ion-Implanted MOSFETs with Very Small
Physical Dimensions. Proc. of Solid-State Circuits, 9(5):256–268, 1974.
[13] H. Esmaeilzadeh, E. Blem, R. St. Amant, K. Sankaralingam, and
D. Burger. Power Limitations and Dark Silicon Challenge the Future of
Multicore. ACM Transactions on Computer Systems, 30(3):1–27, 2012.
[14] N. Hardavellas, M. Ferdman, B. Falsafi, and A. Ailamaki. Toward dark
silicon in servers. IEEE Micro, 31(4):6–15, 2011.
[15] W. Huang, K. Rajamani, M.R. Stan, and K. Skadron. Scaling with design
constraints: Predicting the future of big chips. IEEE Micro, 31(4):16–29,
2011.
[16] M. B. Taylor. Is dark silicon useful? Harnessing the four horsemen
of the coming dark silicon apocalypse. In Proc. of Design Automation
Conference, pages 1131–1136. ACM, 2012.
[17] G. Venkatesh, J. Sampson, N. Goulding, S. Garcia, V. Bryksin,
J. Lugo-Martinez, S. Swanson, and M. B. Taylor. Conservation
cores: Reducing the energy of mature computations. In Int. Conf.
on Architectural Support for Programming Languages and Operating
Systems, pages 205–218. ACM, 2010.
[18] A. Carroll and G. Heiser. Mobile Multicores : Use Them or Waste
Them. ACM SIGOPS Oper. Syst. Rev., 48(1):44–48, 2014.
[19] N. Madan, A. Buyuktosunoglu, P. Bose, and M. Annavaram. A case
for guarded power gating for multi-core processors. 17th Int. Symp. on
HPC Architecture, pages 291–300, 2011.