Abstract
DRAM (dynamic random-access memory) energy consumption in low-power embedded systems can be very high, exceeding that of the data cache or even that of the processor. This paper presents and evaluates a scheme for reducing the energy consumption of SDRAM (synchronous DRAM) memory access by a combination of techniques that take advantage of SDRAM energy efficiencies in bank and row access. This is achieved by using small, cachelike structures in the memory controller to prefetch an additional cache block(s) on SDRAM reads and to combine block writes to the same SDRAM row. The results quantify the SDRAM energy consumption of MiBench applications and demonstrate significant savings in SDRAM energy consumption, 23%, on average, and reduction in the energy-delay product, 44%, on average. The approach also improves performance: the CPI is reduced by 26%, on average.
- Abali, B. and Franke, H. 2000. Operating system support for fast hardware compression of main memory contents. In Memory Wall Workshop, the 27th Annual International Symposium on Computer Architecture.Google Scholar
- Barr, K. and Asanovic, K. 2003. Energy aware lossless data compression. In Proceedings of the First International Conference on Mobile Systems, Applications, and Services, San Francisco, CA. Google Scholar
Digital Library
- Burger, D. and Austin, T. 1997. The simplescalar tool set, version 2.0. Technical Rep. TR-97-1342, Computer Science Department, University of Wisconsin-Madison.Google Scholar
- Dahlgren, F., Dubois, M., and Stenstrom, P. 1993. Fixed and adaptive sequential prefetching in shared-memory multiprocessors. In Proceedings of the International Conference on Parallel Processing. 56--63. Google Scholar
Digital Library
- Ekman, M. and Stenström, P. 2005. A robust main-memory compression scheme. In Proceedings of the 32nd Annual International Symposium on Computer Architecture, Madison, Wisconsin. 74--85. Google Scholar
Digital Library
- Farkas, K., Jouppi, N. P., and Chow, P. 1994. How useful are non-blocking loads, stream buffers, and speculative execution in muliple issue processors. Technical Rep. 94/8, Digital Western Research Laboratory (Dec.)Google Scholar
- Goossens, K., Gangwal, O. P., Röver, J., and Niranjan, A. P. 2004. Interconnect and memory organization in SoCs for advanced set-top boxes and TV — Evolution, analysis and trends. http://www.homepages.inf.ed.ac.uk/kgoossen/2004-interconnectcentric-chap15.pdf.Google Scholar
- Guthaus, M. R., Ringenberg, J. S., Ernst, D., Austin, T. M., Mudge, T., and Brown, R. B. 2001. Mibench: A free, commercially representative embedded benchmark suite. In Proceedings of the IEEE 4th Annual Workshop on Workload Characterization. 83--94. Google Scholar
Digital Library
- Hennessy, J. and Patterson, D. 2006. Computer Architecture A Quantitative Approach. Google Scholar
Digital Library
- Johnson, T. L., Merten, M. C., and Hwu, W. W. 1997. Run-time adaptive cache hierarchy management via reference analysis. In Proceedings of the 24th International Symposium on Computer Architecture, Denver, CO. 315--326. Google Scholar
Digital Library
- Jouppi, N. P. 1990. Improving direct-mapped cache performance by the addition of a small fully-associative cache and prefetch buffers. In Proceedings of the 17th Annual International Symposium on Computer Architecture, Seattle, WA. 364--373. Google Scholar
Digital Library
- Jouppi, N. P. 1993. Cache write policies and performance. In Proceedings of the 20th International Symposium on Computer Architecture, San Diego, CA. Google Scholar
Digital Library
- Kane, G. 1988. MIPS RISC Architecture. Prentice-Hall, Englewood Cleffs, NJ. Google Scholar
Digital Library
- Kim, H. S., Vijaykrishnan, N., Kandemir, M., Brockmeyer, E., Catthoor, F., and Irwin, M. J. 2003. Estimating influence of data layout optimizations on SDRAM energy consumption. In Proceedings of the 2003 International Symposium on Low Power Electronics and Design, Seoul, Korea. 40--43. Google Scholar
Digital Library
- Kumar, S. and Wilkerson, C. 1998. Exploiting spatial locality in data cache using spatial footprint. In Proceedings of the International Symposium on Computer Architecture. Google Scholar
Digital Library
- Lebeck, A. R., Fan, X., Zeng, H., and Ellis, C. 2000. Power aware page allocation. In Proceedings of the 9th International Conference on Architectural Support for Programming Languages and Operating Systems, Cambridge, MA. 105--116. Google Scholar
Digital Library
- Micron. The Micron System-Power Calculator http://www.micron.com/products/dram/syscalc.html.Google Scholar
- MicronDataSheet. The Micron: Synchronous DRAM 64Mb x32 Part number: MT48LC2M32B2 http://download.micron.com/pdf/datasheets/dram/sdram/64MSDRAMx32.pdf.Google Scholar
- Montanaro, J., Witek, R. T., Anne, K., Black, A. J., Cooper, E. M., Dobberpuhl, D. W., Donahue, P. M., Eno, J., Hoeppner, G. W., Kruckemyer, D., Lee, T. H., Lin, P. C. M., Madden, L., Murray, D., Pearce, M. H., Santhanam, S., Snyder, K. J., Stephany, R., and Thierauf, S. C. 1996. A 160--MHz, 32--b, 0.5--W CMOS RISC microprocessor. IEEE J. Solid-State Circuits 31, 11, 1703--1714.Google Scholar
Cross Ref
- Shivakumar, P. and Jouppi, N. 1990. Cacti 3.0: An integrated cache timing, power, and area model. Tech. rep., Digital Equipment Corporation, COMPAQ Western Research Lab.Google Scholar
- Rixner, S., Dally, W. J., Kapasi, U. J., Mattson, P., and Owens, J. D. 2000. Memory access scheduling. In Proceedings of the 27th Annual International Symposium on Computer Architecture, Vancouver, British Columbia, Canada. 128--138. Google Scholar
Digital Library
- Smith, A. J. 1979. Characterizing the storage process and its effect on the update of main memory by write through. J. ACM 26, 1, 6--27. Google Scholar
Digital Library
- Smith, A. J. 1982. Cache memories. ACM Comput. Surv. 14, 3, 473--530. Google Scholar
Digital Library
- Smith, A. J. 1991. Second bibliography on cache memories. SIGARCH Comput. Architecture News 19, 4, 154--182. Google Scholar
Digital Library
- Solihin, Y., Torrellas, J., and Lee, J. 2002. Using a user-level memory thread for correlation prefetching. In Proceedings of 29th Annual International Symposium on Computer Architecture (May), Anchorage, Alaska. 171--182. Google Scholar
Digital Library
- Trajkovic, J. and Veidenbaum, A. 2004. Intelligent memory controller for reducing power consumption in embedded systems. Technical Rep. ICS-TR-04-02, School of Information and Computer Science, University of California at Irvine.Google Scholar
- Veidenbaum, A., Tang, W., Gupta, R., Nicolau, A., and Ji, X. 1999. Adapting cache line size to application behavior. In International Conference on Supercomputing, Rhodes, Greece. 145--154. Google Scholar
Digital Library
- Wattch. Wattch Version 1.02 http://www.eecs.harvard.edu/~dbrooks/sim-wattch-1.02.tar.gz.Google Scholar
- Wilkes, M. V. 1965. Slave memories and dynamic storage allocation. IEEE Trans. Electronic Comput. EC-14, 4, 270--271.Google Scholar
Cross Ref
- Zhang, C., Vahid, F., and Najjar, W. 2005. A highly configurable cache for low energy embedded systems. Trans. Embedded Comput. Sys. 4, 2, 363--387. Google Scholar
Digital Library
Index Terms
Improving SDRAM access energy efficiency for low-power embedded systems
Recommendations
Low-energy off-chip SDRAM memory systems for embedded applications
Memory systems are dominant energy consumers, and thus many energy reduction techniques for memory buses and devices have been proposed. For practical energy reduction practices, we have to take into account the interaction between a processor and cache ...
Shadow Stack Scratch-Pad-Memory for Low Power SoC
SEC '08: Proceedings of the 2008 Fifth IEEE International Symposium on Embedded ComputingIn many embedded system, researches focus on how to use on-chip memory, like SPM, to reduce the energy consumption generated by off-chip memory, such as SDRAM or DRAM. They put the often use instructions and important data into on-chip memory to reduce ...
Energy exploration and reduction of SDRAM memory systems
DAC '02: Proceedings of the 39th annual Design Automation ConferenceIn this paper, we introduce a precise energy characterization of SDRAM main memory systems and explore the amount of energy associated with design parameters, leading to energy reduction techniques that we are able to recommend for practical use.We ...






Comments