Adaptive error protection for energy efficiency

With dramatic scaling in feature sizes, noise resilience is becoming one of the most important design parameters, similar to performance and energy efficiency. Noise resilience is particularly problematic in long on-chip buses of complex single chip systems such as on-chip multiprocessors. While one might opt to employ a very powerful error protection scheme, this may not be very energy efficient as noise behavior typically varies over time. In this paper, we propose an adaptive error protection scheme for energy efficiency, where the type of the coding scheme is modulated dynamically. The idea behind this strategy is to monitor the dynamic variations in noise behavior and use the least powerful (and hence the most energy efficient) error protection scheme required to maintain the error rates below a pre-set threshold. Our detailed experimental results obtained through simulation show that this adaptive strategy achieves the same level of error protection as the most powerful strategy experimented, without experiencing the latter's energy inefficiency. Based on our results, we recommend system designers to adopt adaptive protection schemes in environments where both energy and reliability are important.

[1]  John F. Wakerly,et al.  Digital design - principles and practices , 1990, Prentice Hall Series in computer engineering.

[2]  Anoop Gupta,et al.  The SPLASH-2 programs: characterization and methodological considerations , 1995, ISCA.

[3]  K. L. Shepard,et al.  Noise in deep submicron digital design , 1996, ICCAD 1996.

[4]  Power Supply Noise Analysis Methodology For Deep-submicron Vlsi Chip Design , 1997, Proceedings of the 34th Design Automation Conference.

[5]  William J. Dally,et al.  Digital systems engineering , 1998 .

[6]  Sujit Dey,et al.  Fault modeling and simulation for crosstalk in system-on-chip interconnects , 1999, 1999 IEEE/ACM International Conference on Computer-Aided Design. Digest of Technical Papers (Cat. No.99CH37051).

[7]  Naresh R. Shanbhag,et al.  Reliable low-power design in the presence of deep submicron noise (embedded tutorial session) , 2000, ISLPED '00.

[8]  Naresh R. Shanbhag,et al.  Toward achieving energy efficiency in presence of deep submicron noise , 2000, IEEE Trans. Very Large Scale Integr. Syst..

[9]  Sung-Mo Kang,et al.  Noise-aware power optimization for on-chip interconnect , 2000, ISLPED'00: Proceedings of the 2000 International Symposium on Low Power Electronics and Design (Cat. No.00TH8514).

[10]  Naresh R. Shanbhag,et al.  Soft digital signal processing , 2001, IEEE Trans. Very Large Scale Integr. Syst..

[11]  Luca Benini,et al.  Low power error resilient encoding for on-chip data buses , 2002, Proceedings 2002 Design, Automation and Test in Europe Conference and Exhibition.

[12]  Giovanni De Micheli,et al.  An adaptive low-power transmission scheme for on-chip networks , 2002, 15th International Symposium on System Synthesis, 2002..