Get 20M+ Full-Text Papers For Less Than $1.50/day. Start a 14-Day Trial for You or Your Team.

Learn More →

Cache Reconfiguration Using Machine Learning for Vulnerability-aware Energy Optimization

Cache Reconfiguration Using Machine Learning for Vulnerability-aware Energy Optimization Dynamic cache reconfiguration has been widely explored for energy optimization and performance improvement for single-core systems. Cache partitioning techniques are introduced for the shared cache in multicore systems to alleviate inter-core interference. While these techniques focus only on performance and energy, they ignore vulnerability due to soft errors. In this article, we present a static profiling based algorithm to enable vulnerability-aware energy-optimization for real-time multicore systems. Our approach can efficiently search the space of cache configurations and partitioning schemes for energy optimization while task deadlines and vulnerability constraints are satisfied. A machine learning technique has been employed to minimize the static profiling time without sacrificing the accuracy of results. Our experimental results demonstrate that our approach can achieve 19.2% average energy savings compared with the base configuration, while drastically reducing the vulnerability (49.3% on average) compared to state-of-the-art techniques. Furthermore, the machine learning technique enabled more than 10x speedup in static profiling time with a negligible prediction error of 3%. http://www.deepdyve.com/assets/images/DeepDyve-Logo-lg.png ACM Transactions on Embedded Computing Systems (TECS) Association for Computing Machinery

Cache Reconfiguration Using Machine Learning for Vulnerability-aware Energy Optimization

Download PDF
24 pages

Loading next page...
 
/lp/association-for-computing-machinery/cache-reconfiguration-using-machine-learning-for-vulnerability-aware-WO3gWyhVbt
Publisher
Association for Computing Machinery
Copyright
Copyright © 2019 ACM
ISSN
1539-9087
eISSN
1558-3465
DOI
10.1145/3309762
Publisher site
See Article on Publisher Site

Abstract

Dynamic cache reconfiguration has been widely explored for energy optimization and performance improvement for single-core systems. Cache partitioning techniques are introduced for the shared cache in multicore systems to alleviate inter-core interference. While these techniques focus only on performance and energy, they ignore vulnerability due to soft errors. In this article, we present a static profiling based algorithm to enable vulnerability-aware energy-optimization for real-time multicore systems. Our approach can efficiently search the space of cache configurations and partitioning schemes for energy optimization while task deadlines and vulnerability constraints are satisfied. A machine learning technique has been employed to minimize the static profiling time without sacrificing the accuracy of results. Our experimental results demonstrate that our approach can achieve 19.2% average energy savings compared with the base configuration, while drastically reducing the vulnerability (49.3% on average) compared to state-of-the-art techniques. Furthermore, the machine learning technique enabled more than 10x speedup in static profiling time with a negligible prediction error of 3%.

Journal

ACM Transactions on Embedded Computing Systems (TECS) – Association for Computing Machinery

Published: Apr 2, 2019

Keywords: Vulnerability

References

  • MathWorks, Retrieved from https://www
    Statistics, ; Toolbox, Machine Learning; Matlab,
  • Dynamic phase-based tuning for embedded systems using phase distance mapping
    Adegbija, Tosiron; Gordon-Ross, Ann; Munir, Arslan
  • Balancing performance and reliability in the memory hierarchy
    Asadi, G-H; Mehdi, V. S.; Tahoori, B.; Kaeli, David
  • The gem5 simulator
    Binkert, Nathan; Beckmann, Bradford; Black, Gabriel; Reinhardt, Steven K.; Saidi, Ali; Basu, Arkaprava; Hestness, Joel; Hower, Derek R.; Krishna, Tushar; Sardashti, Somayeh
  • Computing architectural vulnerability factors for address-based structures
    Biswas, Arijit; Racunas, Paul; Cheveresan, Razvan; Emer, Joel; Mukherjee, Shubhendu S.; Rangan, Ram
  • Cache size selection for performance, energy and reliability of time-constrained systems
    Cai, Yuan; Schmitz, Marcus T.; Ejlali, Alireza; Al-Hashimi, Bashir M.; Reddy, Sudhakar M.
  • Static energy reduction by performance linked dynamic cache resizing
    Chakraborty, Shounak; Kapoor, Hemangee K.
  • A white paper on the benefits of chipkill-correct ECC for PC server main memory
    Dell, Timothy J.
  • A self-tuning configurable cache
    Gordon-Ross, Ann; Vahid, Frank
  • MiBench: A free, commercially representative embedded benchmark suite
    Guthaus, Matthew R.; Ringenberg, Jeffrey S.; Ernst, Dan; Austin, Todd M.; Mudge, Trevor; Brown, Richard B.
  • Content-aware encoding for improving energy efficiency in multi-level cell resistive random access memory
    Hajimiri, Hadi; Mishra, Prabhat; Bhunia, Swarup; Long, Branden; Li, Yibo; Jha, Rashmi
  • Synergistic integration of dynamic cache reconfiguration and code compression in embedded systems
    Hajimiri, Hadi; Rahmani, Kamran; Mishra, Prabhat
  • Intra-task dynamic cache reconfiguration
    Hajimiri, Hadi; Mishra, Prabhat
  • SPEC CPU2000: Measuring CPU performance in the new millennium
    Henning, John L.
  • Thread-criticality aware dynamic cache reconfiguration in multi-core system
    Hsu, Po-Yang; Hwang, TingTing
  • Compression-aware dynamic cache reconfiguration for embedded systems
    Hajimiri, Hadi; Rahmani, Kamran; Mishra, Prabhat
  • Vulnerability-aware energy optimization for reconfigurable caches in multitasking systems
    Huang, Yuanwen; Mishra, Prabhat
  • Reliability and energy-aware cache reconfiguration for embedded systems
    Huang, Yuanwen; Mishra, Prabhat
  • Vulnerability-aware energy optimization using reconfigurable caches in multicore systems
    Huang, Yuanwen; Mishra, Prabhat
  • Smart cache cleaning: Energy efficient vulnerability reduction in embedded processors
    Jeyapaul, Reiley; Shrivastava, Aviral
  • Bank-aware dynamic cache partitioning for multicore architectures
    Kaseridis, Dimitris; Stuecheli, Jeffrey; John, Lizy K.
  • Guidelines to design parity protected write-back L1 data cache
    Ko, Yohan; Jeyapaul, Reiley; Kim, Youngbin; Lee, Kyoungwoo; Shrivastava, Aviral
  • Exploring cache bypassing and partitioning for multi-tasking on GPUs
    Liang, Yun; Li, Xiuhong; Xie, Xiaolong
  • Master: A multicore cache energy-saving technique using dynamic cache reconfiguration
    Mittal, Sparsh; Cao, Yanan; Zhang, Zhao
  • A survey of techniques for modeling and improving reliability of computing systems
    Mittal, Sparsh; Vetter, Jeffrey S.
  • A systematic methodology to compute the architectural vulnerability factors for a high-performance microprocessor
    Mukherjee, Shubhendu S.; Weaver, Christopher; Emer, Joel; Reinhardt, Steven K.; Austin, Todd
  • TECS: Temperature- and energy-constrained scheduling for multicore systems
    Qin, Xiaoke; Mishra, Prabhat
  • TCEC: Temperature- and energy-constrained scheduling in real-time multitasking systems
    Qin, Xiaoke; Wang, Weixun; Mishra, Prabhat
  • Neutrons from above
    Rates, Soft Error
  • Memory-based computing for performance and energy improvement in multicore architectures
    Rahmani, Kamran; Mishra, Prabhat; Bhunia, Swarup
  • Cache partitioning for energy-efficient and interference-free embedded multitasking
    Reddy, Rakesh; Petrov, Peter
  • Choosing an error protection scheme for a microprocessor’s L1 data cache
    Sadler, Nathan N.; Sorin, Daniel J.
  • A dynamically reconfigurable cache for multithreaded processors
    Settle, Alex; Connors, Dan; Gibert, Enric; González, Antonio
  • Phase tracking and prediction
    Sherwood, Timothy; Sair, Suleyman; Calder, Brad
  • Reducing data cache susceptibility to soft errors
    Sridharan, Vilas; Asadi, Hossein; Tahoori, Mehdi B.; Kaeli, David
  • A study of DRAM failures in the field
    Sridharan, Vilas; Liberty, Dean
  • Soft error benchmarking of L2 caches with PARMA
    Suh, Jinho; Manoochehri, Mehrtash; Annavaram, Murali; Dubois, Michel
  • A general algorithm for energy-aware dynamic reconfiguration in multitasking systems
    Wang, Weixun; Ranka, Sanjay; Mishra, Prabhat
  • SACR: Scheduling-aware cache reconfiguration for real-time embedded systems
    Wang, Weixun; Mishra, Prabhat; Gordon-Ross, Ann
  • Leakage-aware energy minimization using dynamic voltage scaling and cache reconfiguration in real-time systems
    Wang, Weixun; Mishra, Prabhat
  • Dynamic reconfiguration of two-level caches in soft real-time embedded systems
    Wang, Weixun; Mishra, Prabhat
  • Temperature- and energy-constrained scheduling in multitasking systems: A model checking approach
    Wang, Weixun; Qin, Xiaoke; Mishra, Prabhat
  • Energy-aware dynamic reconfiguration algorithms for real-time multitasking systems
    Wang, Weixun; Ranka, Sanjay; Mishra, Prabhat
  • System-wide leakage-aware energy minimization using dynamic voltage scaling and cache reconfiguration in multitasking systems
    Wang, Weixun; Mishra, Prabhat
  • Dynamic reconfiguration of two-level cache hierarchy in real-time embedded systems
    Wang, Weixun; Mishra, Prabhat
  • Energy-aware dynamic slack allocation for real-time multitasking systems
    Wang, Weixun; Ranka, Sanjay; Mishra, Prabhat
  • Dynamic cache reconfiguration for soft real-time systems
    Wang, Weixun; Mishra, Prabhat; Gordon-Ross, Ann
  • Dynamic cache reconfiguration and partitioning for energy optimization in real-time multi-core systems
    Wang, Weixun; Mishra, Prabhat; Ranka, Sanjay
  • Dynamic Reconfiguration in Real-Time Systems
    Wang, Weixun; Mishra, Prabhat; Ranka, Sanjay
  • A highly configurable cache for low energy embedded systems
    Zhang, Chuanjun; Vahid, Frank; Najjar, Walid
  • An analysis of microarchitecture vulnerability to soft errors on simultaneous multithreaded architectures
    Zhang, Wangyuan; Fu, Xin; Li, Tao; Fortes, José