ABSTRACT
Improving performance, reducing energy consumption and enhancing reliability are three important objectives for embedded computing systems design. In this paper, we study the joint impact of cache size selection on these three objectives. For this purpose, we conduct extensive fault injection experiments on five benchmark examples using a cycle-accurate processor simulator. Performance and reliability are analyzed using the performability metric. Overall, our experiments demonstrate the importance of a careful cache size selection when designing energy-efficient and reliable systems. Furthermore, the experimental results show the existence of optimal or Pareto-optimal cache size selection to optimize the three design objectives.
- J. L. Hennessy, D. A. Patterson, Computer Architecture: A Quantitative Approach, 2nd Edition, Morgan Kaufmann Publishing Co. 1996. Google ScholarDigital Library
- C. Zhang, F. Vahid and R. Lysecky, "A self-Tuning Cache Architecture for Embedded Systems", in Proc. of DATE, 2004. Google ScholarDigital Library
- C. Zhang, F. Vahid, W. Najjar, "A Highly Configurable Cache Architecture for Embedded Systems", in Proc. of International Symposium on Computer Architecture, 2003. Google ScholarDigital Library
- S. Dropsho et al., "Integrating Adaptive On-Chip Storage Structures for Reduced Dynamic Power", in Proc. of the International Conference on Parallel Architectures and Compilation Techniques, 2002. Google ScholarDigital Library
- D. H. Albonesi, "Selective cache ways: On-demand cache resource allocation", in Proc. of International Symposium on Microarchitecutre, 1999. Google ScholarDigital Library
- M. Powell A. Agaewal, T. Vijaykumar, B. Falsafi and K. Roy, "Reducing Set-Associative Cache Energy via Way-Prediction and Selective Direct Mapping", in Proc. of International Symposium on Microarchitecture, 2001. Google ScholarDigital Library
- A. C. Nacul and T. Givargis, "Dynamic Voltage and Cache Reconfiguration for Low Power", in Proc. of DATE 04, March, 2004. Google ScholarDigital Library
- S. Yang, M. D. Powell, B. Falsafi, T. N. Vijaykumar, "Exploiting Choice in Resizable Cache Design to Optimize Deep-Submicron Processor Energy-Delay", in Proc. of International Symposium on High-Performance Computer Architecture, 2002. Google ScholarDigital Library
- G. Asadi, V. Sridharan, M. B. Tahoori, D. Kaeli, "Balancing Performacne and Reliability in the Memory Hierarchy", in Proc. of International Symposium on Performance Analysis of Systems and Software, 2005. Google ScholarDigital Library
- L. Li, V. Degalahal, N. Vijaykrishnan, M. Kandemir, M. J. Irwin, "Soft Error and Energy Consumption interations: A Data Cache Perspective". in Proc. of ISLPED 04, Aug, 2004. Google ScholarDigital Library
- S. Kim and A. K. Somani, "Area Efficient Architectures for Information Integrity in Cache Memories", in Proc. of International Symposium on Computer Architecture, 1999. Google ScholarDigital Library
- W. Zhang, S. Gurumurthi, M. Kandemir, A. Sivasubramaniam, "ICR: in-cache replication for enhancing data cache reliability", in Proc. of International Conference on Dependable Systems and Networks, 2003.Google ScholarCross Ref
- D. Zhu, R. Melhem. and D. Mosse, "The Effecs of Energy Management on Reliability in Real-Time Embedded Systems", in Proc. of ICCAD 04, Nov. 2004. Google ScholarDigital Library
- A. Ejlali, M. T. Schmitz, B. M. Al-Hashimi, S. G. Miremadi, "Energy Efficient SEU-Tolerance in DVS-Enabled Real-Time Systems through Information Redundancy", in Proc. of ISLPED 05, Aug. 2005. Google ScholarDigital Library
- R. Melhem, D. Mosse, E. Elnozahy, "The interplay of Power Management and Fault Recovery in Real-Time Systems", IEEE Transaction on Computers, Vol. 53, No. 2, February, 2004. Google ScholarDigital Library
- H. Hanson, M. S. Hrishikesh, V. Agarwal, S. W. Keckler, D. Burger, "Static Energy Reduction Techniques for Microprocessor Caches", IEEE Transaction on VLSI systems, Vol. 11, No. 3, June, 2003. Google ScholarDigital Library
- S. Mitra, N. Seifert, M. Zhang, Q. Shi, K. S. Kim, "Robust System Design with Built-In Soft-Error Resilience", IEEE Computer Magazine, Vol, 38, No. 2, Feburary, 2005. Google ScholarDigital Library
- P. E. Dodd and F. W. Sexton, "Critical Charge Concepts for the CMOS SRAMS", IEEE Transactions on Nuclear Science, Vol. 42, No. 6, Dec. 1995.Google ScholarCross Ref
- F. Faure, R. Velazco, M. Violante, M. Rebaudengo and M. Sonza Reorda, "Impact of Data Cache Memory on the Single Event Upset-Induced Error Rate of Microprocessors", IEEE Transactions on Nuclear Science, Vol. 50, No. 6, Dec. 2003.Google ScholarCross Ref
- A. Maheshwari, W. Burleson, R. Tessier, "Trading off Transient Fault Tolerance and Power Consumption in Deep Submicron (DSM) VLSI Circuits", IEEE Transaction on VLSI systems, Vol. 12, No. 3, March 2004. Google ScholarDigital Library
- M. Rebaudengo, M. S. Reorda and M. Violante, "An Accurate Analysis of the Effects of Soft Errors in the Instruction and Data Caches of a Pipelined Microprocessor", in Proc. of DATE 03, March, 2003. Google ScholarDigital Library
- L. Li, I. Kadayif, Y-F. Tsai, N. Vijaykrishnan, M. Kandemir, M. J. Irwin and A. Sivsubramaniam, "Leakage Energy Management in Cache Hierarchies", in Proc. of International Conference on Parallel Architectures and Compilation Techniques, 2002. Google ScholarDigital Library
- G. Reinmann and N. P. Jouppi, "CACTI2.0: An Integrated Cache Timing and Power Model", COMPAQ, Western Research Lab, Research Report, 2000.Google Scholar
- http://www-micrel.deis.unibo.it/sitonew/research/mparm.htmlGoogle Scholar
Index Terms
- Cache size selection for performance, energy and reliability of time-constrained systems
Recommendations
Heterogeneous way-size cache
ICS '06: Proceedings of the 20th annual international conference on SupercomputingSet-associative cache architectures are commonly used. These caches consist of a number of ways, each of the same size. We have observed that the different ways have very different utilization, which motivates the design of caches with heterogeneous way ...
Towards a performance- and energy-efficient data filter cache
ODES '13: Proceedings of the 10th Workshop on Optimizations for DSP and Embedded SystemsAs CPU data requests to the level-one (L1) data cache (DC) can represent as much as 25% of an embedded processor's total power dissipation, techniques that decrease L1 DC accesses can significantly enhance processor energy efficiency. Filter caches are ...
Comments