Selective wordline voltage boosting for caches to manage yield under process variations

ABSTRACT

One of the most important hurdles of technology scaling is process variations, i.e., variations in device characteristics. Process variations cause large fluctuations in performance and power consumption in the manufactured chips. In addition, these fluctuations cause reductions in the chip yields. In this work, we present an analysis of a representative high-performance processor architecture and show that the caches have the highest probability of causing yield losses under process variations. We then propose a novel selective wordline voltage boosting mechanism that aims at reducing the latency of the cache lines that are affected by process variations. We show that our approach can eliminate over 80% of the yield losses under medium level of variations, while incurring less than 1% per-access energy overhead on average and less than 4.5% area overhead.

REFERENCES

• 1: A. Agarwal, et al., "A process-tolerant cache architecture for improved yield in nanoscale technologies", IEEE Transaction on VLSI Systems, vol. 13, pp. 27--38, 2005.
• 2: A. Agarwal, et al., "Process variation in embedded memories: failure analysis and variation aware architecture", IEEE Jnl. of Solid-State Circuits, vol. 40, 2005.
• 3: S. Borkar, et al., "Parameter variations and impact on circuits and microarchitecture". In Proc. of DAC, 2003.
• 4: K. A. Bowman, et al., "Impact of Die-to-Die and Within-Die Parameter Fluctuations on the Maximum Clock Frequency Distribution for Gigascale Integration". IEEE Jnl. of Solid-State Circuits, vol. 37, 2002.
• 5: W. Bryg and J. Alabado, "The UltraSPARC T1 Processor - Reliability, Availability, and Serviceability."
• 6: G. K. Chen, et al., "Yield-driven near-threshold SRAM design". In Proc. of Int'l Conference on Computer Aided Design, 2007.
• 7: T. Chen and S. Naffziger. "Comparison of Adaptive Body Bias (ABB) and Adaptive Supply Voltage (ASV) for Improving Delay and Leakage under the Presence of Process Variation". IEEE Transaction on VLSI Systems, vol. 11, pp. 888--899, 2003.
• 8: A. Das, S. Ozdemir, G. Memik, J. Zambreno, and A. N. Choudhary, "Microarchitectures for Managing Chip Revenues under Process Variations". Computer Architecture Letters, vol. 6, pp. 29--32, 2007.
• 9: J. Friedrich, et al., "Design of the Power6 Microprocessor", In ISSCC, 2007.
• 10: J. Gregg and T. W. Chen. "Post Silicon Power/Performance Optimization in the Presence of Process Variations Using Individual Well Adaptive Body Biasing (IWABB)". In proceedings of IEEE Int'l Symposium on Quality Electronic Design, 2007.
• 11: F. Hamzaoglu, et al., "A 153Mb-SRAM Design with Dynamic Stability Enhancement and Leakage Reduction in 45nm High-k Metal-Gate CMOS Technology", In Proc. of Int'l Solid State Circuits Conference, 2008.
• 12: N. P. Jouppi, "Improving direct-mapped cache performance by the addition of a small fully-associative cache and prefetch buffers", ACM SIGARCH Computer Architecture News, vol. 18, 1990.
• 13: C. Kim, D. Burger, and S. W. Keckler. "An adaptive, non-uniform cache structure for wire-delay dominated on-chip caches". In Proc. of Int'l Conference on Architectural Support for Programming Languages and Operating Systems, 2002.
• 14: N. Kim, et al., "Single-VDD and single-VT super-drowsy techniques for low-leakage high-performance instruction caches", In Proc. of Int'l Symposium on Low Power Electronics and Design, 2004.
• 15: K. Krewell, Alpha EV7 Processor: A High-Performance Tradition Continues, Apr. 2002.
• 16: H. Li, et al., "SAVS: a self-adaptive variable supply-voltage technique for process- tolerant and power-efficient multi-issue superscalar processor design". In Proc. of ASPDAC, 2006.
• 17: X. Liang, et al., "Process Variation Tolerant 3T1D-Based Cache Architectures". In Proc. of IEEE/ACM Int'l Symposium on Microarchitecture, 2007.
• 18: M. Mutyam and N. Vijaykrishnan. "Working with process variation aware caches". In proc. of DATE, 2007.
• 19: S. Naffziger, et al., "The Implementation of the Itanium 2 Microprocessor," IEEE Jnl. of Solid-State Circuits, vol. 37, 2002.
• 20: S. R. Nassif. "Modeling and Analysis of Manufacturing Variations". In Proc. of IEEE Conf. on Custom Integrated Circuits, 2001.
• 21: S. Ozdemir, D. Sinha, G. Memik, J. Adams, and H. Zhou, "Yield-Aware Cache Architectures". In Proc. of IEEE/ACM Int'l Symposium on Microarchitecture, pp. 15--25, 2006.
• 22: M. Powell, et al., "Gated-Vdd: A circuit technique to reduce leakage in deep-submicron cache memories", ISLPED, pp. 90--95, 2000.
• 23: Predictive Technology Model (PTM), Arizona State University. http://www.eas.asu.edu/~ptm/
• 24: M. Riley, et al., "Implementation of the 65nm Cell Broadband Engine", In Proc. of IEEE Custom Integrated Circuits Conf., 2007.
• 25: B. F. Romanescu, et al., "Reducing the Impact of Intra-Core Process Variability with Criticality-Based Resource Allocation and Prefetching". In Proc. of ACM Int'l Conference on Computing Frontiers, 2008.
• 26: T. Sakurai and A. R. Newton. "Alpha-Power Law MOSFET Model and its Applications to CMOS Inverter Delay and Other Formulas", IEEE Jnl. of Solid-State Circuits, vol. 25, pp. 584--594, 1990.
• 27: S. R. Sarangi, et al., "VARIUS: A Model of Process Variation and Resulting Timing Errors for Microarchitects", IEEE Transactions on Semiconductor Manufacturing, vol. 21, pp. 3--13, 2008.
• 28: T. Sherwood, et al., "Automatically characterizing large scale program behavior". In Proc. of Int'l Conference on Architectural Support for Programming Languages and Operating Systems, 2002.
• 29: P. Shivakumar, et al., "Exploiting microarchitectural redundancy for defect tolerance". In Proc. of IEEE Int'l Conference on Computer Design, 2003.
• 30: SIA. International Technology Roadmap for Semiconductors, 2005. Available at http://public.itrs.net.
• 31: SimpleScalar toolset. http://www.simplescalar.com.
• 32: G. S. Sohi, "Cache Memory Organization to Enhance the Yield of High Performance VLSI Processors". IEEE Transaction on Computers, vol. 38, pp. 484--492, 1989.
• 33: R. Teodorescu, et al., "Mitigating Parameter Variation with Dynamic Fine-Grain Body Biasing". In Proc. of IEEE/ACM Int'l Symposium on Microarchitecture, pp. 27--42, 2007.
• 34: The R Project for Statistical Computing. Available from: http://www.r-project.org.
• 35: S. Thoziyoor, et al., "CACTI 5 Technical Report. HP Labs".
• 36: J. Tschanz, K. A. Bowman, and V. De. "Variation-tolerant circuits: circuit solutions and techniques". In Proc. of Design Automation Conference, pp. 762--763, 2005.
• 37: B. Zhai, et al., "The limit of dynamic voltage scaling and insomniac dynamic voltage scaling", IEEE Transaction on VLSI Systems, vol. 13, pp. 1239--1252, 2005

INDEX TERMS

Primary Classification:
  B. Hardware
  B.3 MEMORY STRUCTURES
      B.3.2 Design Styles
          Subjects: Cache memories

General Terms:
Design, Performance, Reliability

Keywords:
access time failure, cache, process variations, selective wordline voltage boosting, yield