ABSTRACT
Across applications, DRAM is a significant contributor to the overall system power, with the DRAM access energy per bit up to three orders of magnitude higher compared to on-chip memory accesses. To improve the power efficiency, DRAM technology incorporates multiplepower-down modes, each with different trade-offs between achievable power savings and performance impact due to entry and exit delay requirements. Accurate modeling of these low power modes and entry and exit control is crucial to analyze the trade-offs across controller configurations and workloads with varied memory access characteristics. To address this, we integrate the power-down modes into the DRAM controller model in the open-source simulator gem5. This is the first publicly available full-system simulator with DRAM power-down modes, providing the research community a tool for DRAM power analysis for a breadth of use cases. We validate the power-down functionality with sweep tests, which trigger defined memory access characteristics. We further evaluate the model with real HPC workloads, illustrating the value of integrating low power functionality into a full system simulator.
- Sara Alspaugh, Arka Bhattacharya, David Culler, and Randy Katz. 2011. The Tao of Systems: Doing Nothing Well.Google Scholar
- Raid Zuhair Ayoub, Krishnam Raju Indukuri, and Tajana Simunic Rosing. 2010. Energy Efficient Proactive Thermal Management in Memory Subsystem. In Proceedings of the 16th ACM/IEEE International Symposium on Low Power Electronics and Design (ISLPED '10). ACM, New York, NY, USA, 195--200. Google ScholarDigital Library
- Nathan Binkert, Bradford Beckmann, Gabriel Black, Steven K. Reinhardt, Ali Saidi, Arkaprava Basu, Joel Hestness, Derek R. Hower, Tushar Krishna, Somayeh Sardashti, Rathijit Sen, Korey Sewell, Muhammad Shoaib, Nilay Vaish, Mark D. Hill, and David A. Wood. 2011. The gem5 simulator. SIGARCH Comput. Archit. News 39, 2 (Aug. 2011), 1--7. Google ScholarDigital Library
- Aaron Carroll and Gernot Heiser. 2013. The Systems Hacker's Guide to the Galaxy Energy Usage in a Modern Smartphone. In Proceedings of the 4th Asia-Pacific Workshop on Systems (APSys '13). ACM, New York, NY, USA, Article 5, 7 pages. Google ScholarDigital Library
- Karthik Chandrasekar, Benny Akesson, and Kees Goossens. 2012. Run-time Power-down Strategies for Real-time SDRAM Memory Controllers. In Proceedings of the 49th Annual Design Automation Conference (DAC '12). ACM, New York, NY, USA, 988--993. Google ScholarDigital Library
- Karthik Chandrasekar, Christian Weis, Yonghui Li, Benny Akesson, Omar Naji, Matthias Jung, Norbert Wehn, and Kees Goossens. {n. d.}. DRAMPower: Open-source DRAM power & energy estimation tool. http://www.drampower.info. ({n. d.}).Google Scholar
- Niladrish Chatterjee, Rajeev Balasubramonian, Manjunath Shevgoor, Seth Pugsley, Aniruddha Udipi, Ali Shafiee, Manu Sudan, Kshitij amd Awasthi, and Zeshan Chishti. 2012. USIMM: the Utah SImulated Memory Module, A Simulation Infrastructure for the JWAC Memory Scheduling Championship. Utah and Intel Corp. (February 2012).Google Scholar
- Victor Delaluz, Mahmut Kandemir, N. Vijaykrishnan, Anand Sivasubramaniam, and Mary Jane Irwin. 2001. Hardware and Software Techniques for Controlling DRAM Power Modes. IEEE Trans. Comput. 50, 11 (Nov. 2001), 1154--1173. Google ScholarDigital Library
- Aditya M. Deshpande, Jeffrey T. Draper, J. Brian Rigdon, and Richard F. Barrett. 2015. PathFinder: A Signature-search Miniapp and Its Runtime Characteristics. In Proceedings of the 5th Workshop on Irregular Applications: Architectures and Algorithms (IA3 '15). ACM, New York, NY, USA, Article 9, 4 pages. Google ScholarDigital Library
- Jack Dongarra, Michael A. Heroux, and Piotr Luszczek. 2016. A new metric for ranking high-performance computing systems. National Science Review 3, 1 (2016), 30.Google ScholarCross Ref
- Hossein Falaki, Ratul Mahajan, Srikanth Kandula, Dimitrios Lymberopoulos, Ramesh Govindan, and Deborah Estrin. 2010. Diversity in Smartphone Usage. In Proceedings of the 8th International Conference on Mobile Systems, Applications, and Services (MobiSys '10). ACM, New York, NY, USA, 179--194. Google ScholarDigital Library
- Xiaobo Fan, Carla Ellis, and Alvin Lebeck. 2001. Memory Controller Policies for DRAM Power Management. In Proceedings of the 2001 International Symposium on Low Power Electronics and Design (ISLPED '01). ACM, New York, NY, USA, 129--134. Google ScholarDigital Library
- N. Farahini, A. Hemani, A. Lansner, F. Clermidy, and C. Svensson. 2014. A scalable custom simulation machine for the Bayesian Confidence Propagation Neural Network model of the brain. In Design Automation Conference (ASP-DAC), 2014 19th Asia and South Pacific. 578--585.Google Scholar
- A. Hansson, N. Agarwal, A. Kolli, T. Wenisch, and A.N. Udipi. 2014. Simulating DRAM controllers for future system architecture exploration. In Performance Analysis of Systems and Software (ISPASS), 2014 IEEE International Symposium on. 201--210.Google Scholar
- Hai Huang, Kang G. Shin, Charles Lefurgy, Tom Keller, Krishna T. Malladi, Ian Shaeffer, Liji Gopalakrishnan, David Lo, Benjamin C. Lee, and Mark Horowitz. 2005. Improving Energy Efficiency by Making DRAM Less Randomly Accessed. In Proceedings of the 2005 International Symposium on Low Power Electronics and Design (ISLPED '05). ACM, New York, NY, USA, 393--398. Google ScholarDigital Library
- I. Hur and C. Lin. 2008. A comprehensive approach to DRAM power management. In 2008 IEEE 14th International Symposium on High Performance Computer Architecture. 305--316.Google Scholar
- Bruce Jacob. 2009. The Memory System: You Can'T Avoid It, You Can'T Ignore It, You Can'T Fake It. Morgan and Claypool Publishers. Google ScholarDigital Library
- B. Jacob, S. Ng, and D. Wang. 2010. Memory Systems: Cache, DRAM, Disk. Elsevier Science. Google ScholarDigital Library
- Radhika Jagtap, Stephan Diestelhorst, Andreas Hansson, Matthias Jung, and Norbert Wehn. 2016. Exploring System Performance using Elastic Traces: Fast, Accurate and Portable. In IEEE International Conference on Embedded Computer Systems Architectures Modeling and Simulation (SAMOS), July, 2016, Samos Island, Greece.Google Scholar
- Min Kyu Jeong, Doe Hyun Yoon, and Mattan Erez. {n. d.}. DrSim: A Platform for Flexible DRAM System Research. http://lph.ece.utexas.edu/public/DrSim. ({n. d.}).Google Scholar
- Matthias Jung. 2017. System-Level Modeling, Analysis and Optimization of DRAM Memories and Controller Architectures. Ph.D. Dissertation. University of Kaiserslautern.Google Scholar
- Matthias Jung, Irene Heinrich, Marco Natale, Deepak M. Mathew, Christian Weis, Sven Krumke, and Norbert Wehn. 2016. ConGen: An Application Specific DRAM Memory Controller Generator. In International Symposium on Memory Systems (MEMSYS 2016). Google ScholarDigital Library
- Matthias Jung, Kira Kraft, and Norbert Wehn. 2017. A New State Model for DRAMs Using Petri Nets. In IEEE International Conference on Embedded Computer Systems Architectures Modeling and Simulation (SAMOS).Google ScholarCross Ref
- Matthias Jung, Christian Weis, and Norbert Wehn. 2015. DRAMSys: A flexible DRAM Subsystem Design Space Exploration Framework. IPSJ Transactions on System LSI Design Methodology (T-SLDM) (August 2015).Google Scholar
- Matthias Jung, Christian Weis, Norbert Wehn, and Karthik Chandrasekar. 2013. TLM modelling of 3D stacked wide I/O DRAM subsystems: a virtual platform for memory controller design space exploration. In Proceedings of the 2013 Workshop on Rapid Simulation and Performance Evaluation: Methods and Tools (RAPIDO '13). ACM, New York, NY, USA, Article 5, 6 pages. Google ScholarDigital Library
- M. Jung, C. Weis, N. Wehn, M. Sadri, and L. Benini. 2014. Optimized active and power-down mode refresh control in 3D-DRAMs. In Very Large Scale Integration (VLSI-SoC), 2014 22nd International Conference on. 1--6.Google Scholar
- Gokcen Kestor, Roberto Gioiosa, and Adolfy Kerbyson, Darren J. and Hoisie. 2013. Quantifying the energy cost of data movement in scientific applications. In Proceedings of the 2013 IEEE International Symposium on Workload Characterization (IISCW 2013). IEEE.Google ScholarCross Ref
- Y. Kim, W. Yang, and O. Mutlu. 2015. Ramulator: A Fast and Extensible DRAM Simulator. IEEE Computer Architecture Letters PP, 99 (2015), 1--1. Google ScholarDigital Library
- J. Krueger, D. Donofrio, J. Shalf, M. Mohiyuddin, S. Williams, L. Oliker, and F.-J. Pfreundt. 2011. Hardware/software co-design for energy-efficient seismic modeling. In High Performance Computing, Networking, Storage and Analysis (SC), 2011 International Conference for. 1--12. Google ScholarDigital Library
- Alvin R. Lebeck, Xiaobo Fan, Heng Zeng, and Carla Ellis. 2000. Power Aware Page Allocation. In Proceedings of the Ninth International Conference on Architectural Support for Programming Languages and Operating Systems (ASPLOS IX). ACM, New York, NY, USA, 105--116. Google ScholarDigital Library
- Piotr R Luszczek, David H Bailey, Jack J Dongarra, Jeremy Kepner, Robert F Lucas, Rolf Rabenseifner, and Daisuke Takahashi. 2006. The HPC Challenge (HPCC) Benchmark Suite. In Proceedings of the 2006 ACM/IEEE Conference on Supercomputing (SC '06). ACM, New York, NY, USA, Article 213. Google ScholarDigital Library
- Krishna T. Malladi, Ian Shaeffer, Liji Gopalakrishnan, David Lo, Benjamin C. Lee, and Mark Horowitz. 2012. Rethinking DRAM Power Modes for Energy Proportionality. In MICRO. Google ScholarDigital Library
- Jedec Solid State Technology Association. 2012. DDR3 SDRAM (JESD 79--3). (2012).Google Scholar
- JEDEC Solid State Technology Association. 2015. High Bandwidth Memory (HBM) DRAM. JEDEC Standard JESD235A (2015).Google Scholar
- Micron Technology, Inc. 2016. DDR4 SDRAM - MT40A2G4. (2016). https://www.micron.com/products/dram/ddr4-sdram/8Gb#/Google Scholar
- David Meisner, Brian T. Gold, and Thomas F. Wenisch. 2009. PowerNap: Eliminating Server Idle Power. In Proceedings of the 14th International Conference on Architectural Support for Programming Languages and Operating Systems (ASPLOS XIV). ACM, New York, NY, USA, 205--216. Google ScholarDigital Library
- Micron. 2011. DDR3 SDRAM System Power Calculator,. last access 2014-07-03. (jul 2011). http://www.micron.com/products/support/power-calcGoogle Scholar
- A. Petitet, R. C. Whaley, J. Dongarra, and A. Cleary. 2016. HPL - A Portable Implementation of the High-Performance Linpack Benchmark for Distributed-Memory Computers. (2016). http://www.netlib.org/benchmark/hpl/Google Scholar
- Scott Rixner, William J. Dally, Ujval J. Kapasi, Peter Mattson, and John D. Owens. 2000. Memory Access Scheduling. In Proceedings of the 27th Annual International Symposium on Computer Architecture (ISCA '00). ACM, New York, NY, USA, 128--138. Google ScholarDigital Library
- P. Rosenfeld, E. Cooper-Balis, and B. Jacob. 2011. DRAMSim2: A Cycle Accurate Memory System Simulator. Computer Architecture Letters 10, 1 (Jan 2011), 16--19. Google ScholarDigital Library
- Daniel Schmidt and Norbert Wehn. 2009. DRAM Power Management and Energy Consumption: a Critical Assessment. In Proceedings of the 22nd Annual Symposium on Integrated Circuits and System Design. Natal, Brazil. Google ScholarDigital Library
- A. Sridhar, A. Vincenzi, M. Ruggiero, Thomas Brunschwiler, and D. Atienza. 2010. 3D-ICE: Fast compact transient thermal modeling for 3D ICs with inter-tier liquid cooling. In Proc. of ICCAD 2010. Google ScholarDigital Library
- Daisuke Takahash. 2014. FFTE: A Fast Fourier Transform Package. (2014). http://www.ffte.jp/Google Scholar
- G. Thomas, K. Chandrasekar, B. Åkesson, B. Juurlink, and K. Goossens. 2012. A Predictor-Based Power-Saving Policy for DRAM Memories. In 2012 15th Euromicro Conference on Digital System Design. 882--889. Google ScholarDigital Library
- Christian Weis, Matthias Jung, Peter Ehses, Cristiano Santos, Pascal Vivet, Sven Goossens, Martijn Koedam, and Norbert Wehn. 2015. Retention Time Measurements and Modelling of Bit Error Rates of WIDE I/O DRAM in MPSoCs. In Proceedings of the IEEE Conference on Design, Automation & Test in Europe (DATE). European Design and Automation Association. Google ScholarDigital Library
Index Terms
- Integrating DRAM power-down modes in gem5 and quantifying their impact
Recommendations
A Bank-Wise DRAM Power Model for System Simulations
RAPIDO '17: Proceedings of the 9th Workshop on Rapid Simulation and Performance Evaluation: Methods and ToolsDRAM devices contribute significantly to the power consumption of today's computing systems. As the DRAM banks are getting denser, bank-wise power contribution is becoming more and more significant in modern DRAM devices. Therefore, DDR3 and LPDDR3/4 ...
Power management of hybrid DRAM/PRAM-based main memory
DAC '11: Proceedings of the 48th Design Automation ConferenceHybrid main memory consisting of DRAM and non-volatile memory is attractive since the non-volatile memory can give the advantage of low standby power while DRAM provides high performance and better active power. In this work, we address the power ...
A power and temperature aware DRAM architecture
DAC '08: Proceedings of the 45th annual Design Automation ConferenceTechnological advances enable modern processors to utilize increasingly larger DRAMs with rising access frequencies. This is leading to high power consumption and operating temperature in DRAM chips. As a result, temperature management has become a real ...
Comments