Reliability modeling and management in dynamic microprocessor-based systems

ABSTRACT

Reliability failure mechanisms, such as time dependent dielectric breakdown, electromigration, and thermal cycling have become a key concern in processor design. The traditional approach to reliability qualification assumes that the processor will operate at maximum performance continuously under worst case voltage and temperature conditions. However, the typical processor spends a very small fraction of its operational time at maximum voltage and temperature. In this paper, we show how this results in a reliability "slack" that can be leveraged to provide increased performance during periods of peak processor demand. We develop a novel, real time reliability model based on workload driven conditions. We then propose a new dynamic reliability management (DRM) scheme that results in 20-35% performance improvement during periods of peak computational demand while ensuring the required reliability lifetime.

REFERENCES

• 1: Jayanth Srinivasan , Sarita V. Adve , Pradip Bose , Jude A. Rivers, The Case for Lifetime Reliability-Aware Microprocessors, Proceedings of the 31st annual international symposium on Computer architecture, p.276, June 19-23, 2004, München, Germany
• 2: Zhijian Lu , Wei Huang , J. Lach , M. Stan , K. Skadron, Interconnect lifetime prediction under dynamic stress for reliability-aware design, Proceedings of the 2004 IEEE/ACM International conference on Computer-aided design, p.327-334, November 07-11, 2004 [doi>10.1109/ICCAD.2004.1382595]
• 3: M. A. Miner, "Cumulative damage in fatigue," Journal of App. Mech. 67,1945.
• 4: J. H. Stathis, "Physical and Predictive Models of Ultra Thin Oxide Reliability in CMOS Devices and Circuits," IEEE Trans. Dev. & Mater. Reliabil. 1, 2001.
• 5: R. Degraeve, et al, "A consistent model for intrinsic breakdown in ultra-thin oxides," Int. Electron Devices Meeting, p. 866, 1995.
• 6: J. R. Black, "Electromigration failure modes for aluminum metallization in semiconductor devices," Proc.of IEEE 57, 1969.
• 7: Mario R. Casu , Mariagrazia Graziano , Guido Masera , Gianluca Piccinini , Maurizio Zamboni, An electromigration and thermal model of power wires for a priori high-level reliability prediction, IEEE Transactions on Very Large Scale Integration (VLSI) Systems, v.12 n.4, p.349-358, April 2004 [doi>10.1109/TVLSI.2004.825599]
• 8: Anantha P. Chandrakasan , William J. Bowhill , Frank Fox, Design of High-Performance Microprocessor Circuits, Wiley-IEEE Press, 2000
• 9: R. C. Blish, II, "Thermal cycling and thermal shock failure rate modeling," Proc. Int. Reliability Physics Symp., 1997.
• 10: Nelson, Wayne, Accelerated Testing: Statistical Models, Test Plans and Data Analyses, John Wiley & Sons, Inc., New York, 1990.
• 11: K. Skadron, et al, "HotSpot: Techniques for modeling thermal effects at the processor-architecture level," Int. Workshop on THERMal Investigations of ICs and Sys., 2002

INDEX TERMS

Primary Classification:
  B. Hardware
  B.8 Performance and Reliability
      B.8.0 General

General Terms:
Design, Management, Performance, Reliability

Keywords:
dynamic reliability management, electromigration, modeling, oxide breakdown, thermal cycling