Abstract
The bottleneck between the processing elements and memory is the biggest issue contributing to the scalability problem in computing. In-memory computation is an alternative approach that combines memory and processor in the same location, and eliminates the potential memory bottlenecks. Associative processors are a promising candidate for in-memory computation, however the existing implementations have been deemed too costly and power hungry. Approximate computing is another promising approach for energy-efficient digital system designs where it sacrifices the accuracy for the sake of energy reduction and speedup in error-resilient applications. In this study, approximate in-memory computing is introduced in memristive associative processors. Two approximate computing methodologies are proposed; bit trimming and memristance scaling. Results show that the proposed methods not only reduce energy consumption of in-memory parallel computing but also improve their performance. As compared to other existing approximate computing methodologies on different architectures (e.g., CPU, GPU, and ASIC), approximate memristive in-memory computing exhibits better results in terms of energy reduction (up to 80x) and speedup (up to 20x) on a variety of benchmarks from different domains when quality degradation is limited to 10% and it confirms that memristive associative processors provide a highly-promising platform for approximate computing.
- Ting Chang, Sung-Hyun Jo, and Wei Lu. 2011. Short-Term Memory to Long-Term Memory Transition in a Nanoscale Memristor. ACS Nano 5, 9 (2011), 7669--7676. PMID: 21861506.Google Scholar
Cross Ref
- L. Chua. 1971. Memristor-The missing circuit element. IEEE Transactions on Circuit Theory 18, 5 (Sep 1971), 507--519.Google Scholar
Cross Ref
- A. H. Edwards, H. J. Barnaby, K. A. Campbell, M. N. Kozicki, W. Liu, and M. J. Marinella. 2015. Reconfigurable Memristive Device Technologies. Proc. IEEE 103, 7 (July 2015), 1004--1033.Google Scholar
Cross Ref
- K. Eshraghian, K. R. Cho, O. Kavehei, S. K. Kang, D. Abbott, and S. M. S. Kang. 2011. Memristor MOS Content Addressable Memory (MCAM): Hybrid Architecture for Future High Performance Search Engines. IEEE Transactions on Very Large Scale Integration (VLSI) Systems 19, 8 (Aug 2011), 1407--1417. Google Scholar
Digital Library
- Hadi Esmaeilzadeh, Adrian Sampson, Luis Ceze, and Doug Burger. 2012. Neural Acceleration for General-Purpose Approximate Programs. In Proceedings of the 2012 45th Annual IEEE/ACM International Symposium on Microarchitecture (MICRO-45). IEEE Computer Society, Washington, DC, USA, 449--460. Google Scholar
Digital Library
- Caxton C. Foster. 1976. Content Addressable Parallel Processors. John Wiley 8 Sons, Inc., New York, NY, USA. Google Scholar
Digital Library
- Fujitsu Semiconductor Limited. 2016. 4M (512 K Ã amp;Uring; 8) Bit SPI Memory ReRAM Datasheet. (12 2016). DOI:http://www.fujitsu.com/global/documents/products/devices/semiconductor/memory/reram/MB85AS4MT-DS501-00045-1v0-E.pdfGoogle Scholar
- Daniele Garbin, Elisa Vianello, Quentin Rafhay, Mourad Azzaz, Philippe Candelier, Barbara DeSalvo, Gerard Ghibaudo, and Luca Perniola. 2016. Resistive memory variability: A simplified trap-assisted tunneling model. Solid-State Electronics 115, Part B (2016), 126--132. Selected papers from the EUROSOI-ULIS conference.Google Scholar
- Qing Guo, Xiaochen Guo, Ravi Patel, Engin Ipek, and Eby G. Friedman. 2013. AC-DIMM: Associative Computing with STT-MRAM. SIGARCH Comput. Archit. News 41, 3 (June 2013), 189--200. Google Scholar
Digital Library
- Y. Halawani, B. Mohammad, D. Homouz, M. Al-Qutayri, and H. Saleh. 2016. Modeling and Optimization of Memristor and STT-RAM-Based Memory for Low-Power Applications. IEEE Transactions on Very Large Scale Integration (VLSI) Systems 24, 3 (March 2016), 1003--1014. Google Scholar
Digital Library
- M. Imani, D. Peroni, A. Rahimi, and T. Rosing. 2017. Resistive CAM Acceleration for Tunable Approximate Computing. IEEE Transactions on Emerging Topics in Computing PP, 99 (2017), 1--1.Google Scholar
- M. Imani, A. Rahimi, and T. S. Rosing. 2016. Resistive configurable associative memory for approximate computing. In 2016 Design, Automation Test in Europe Conference Exhibition (DATE). 1327--1332. Google Scholar
Digital Library
- Georgios Karakonstantis, Debabrata Mohapatra, and Kaushik Roy. 2012. Logic and Memory Design Based on Unequal Error Protection for Voltage-scalable, Robust and Adaptive DSP Systems. J. Signal Process. Syst. 68, 3 (Sept. 2012), 415--431. Google Scholar
Digital Library
- U. R. Karpuzcu, N. S. Kim, and J. Torrellas. 2013. Coping with Parametric Variation at Near-Threshold Voltages. IEEE Micro 33, 4 (July 2013), 6--14. Google Scholar
Digital Library
- Kyung Min Kim, J. Joshua Yang, John Paul Strachan, Emmanuelle Merced Grafals, Ning Ge, Noraica Davila Melendez, Zhiyong Li, and R. Stanley Williams. 2016. Voltage divider effect for the improvement of variability and endurance of TaOx memristor. Scientific Reports 6 (02 Feb 2016), 20085 EP --. Article.Google Scholar
- H. H. Li, Y. Chen, C. Liu, J. P. Strachan, and N. Davila. 2017. Looking Ahead for Resistive Memory Technology: A broad perspective on ReRAM technology for future storage and computing. IEEE Consumer Electronics Magazine 6, 1 (Jan 2017), 94--103.Google Scholar
Cross Ref
- J. Li, R. K. Montoye, M. Ishii, and L. Chang. 2014. 1 Mb 0.41 2T-2R Cell Nonvolatile TCAM With Two-Bit Encoding and Clocked Self-Referenced Sensing. IEEE Journal of Solid-State Circuits 49, 4 (April 2014), 896--907.Google Scholar
Cross Ref
- S. Li, C. Xu, Q. Zou, J. Zhao, Y. Lu, and Y. Xie. 2016. Pinatubo: A processing-in-memory architecture for bulk bitwise operations in emerging non-volatile memories. In 2016 53nd ACM/EDAC/IEEE Design Automation Conference (DAC). 1--6. Google Scholar
Digital Library
- Feng Miao, John Paul Strachan, J. Joshua Yang, Min-Xian Zhang, Ilan Goldfarb, Antonio C. Torrezan, Peter Eschbach, Ronald D. Kelley, Gilberto Medeiros-Ribeiro, and R. Stanley Williams. 2011. Anatomy of a Nanoscale Conduction Channel Reveals the Mechanism of a High-Performance Memristor. Advanced Materials 23, 47 (2011), 5633--5640.Google Scholar
Cross Ref
- Sasa Misailovic, Stelios Sidiroglou, Henry Hoffmann, and Martin Rinard. 2010. Quality of Service Profiling. In Proceedings of the 32Nd ACM/IEEE International Conference on Software Engineering - Volume 1 (ICSE ’10). ACM, New York, NY, USA, 25--34. Google Scholar
Digital Library
- Sparsh Mittal. 2016. A Survey of Techniques for Approximate Computing. ACM Comput. Surv. 48, 4, Article 62 (March 2016), 33 pages. Google Scholar
Digital Library
- D. Mohapatra, V.K. Chippa, A. Raghunathan, and K. Roy. 2011. Design of voltage-scalable meta-functions for approximate computing. In Design, Automation Test in Europe Conference Exhibition (DATE), 2011. 1--6.Google Scholar
- Jerry L. Potter. 1991. Associative Computing: A Programming Paradigm for Massively Parallel Computers. Perseus Publishing. Google Scholar
Digital Library
- A. Rahimi, A. Ghofrani, K. T. Cheng, L. Benini, and R. K. Gupta. 2015. Approximate associative memristive memory for energy-efficient GPUs. In 2015 Design, Automation Test in Europe Conference Exhibition (DATE). 1497--1502. Google Scholar
Digital Library
- D. C. Ralph and M. D. Stiles. 2008. Spin transfer torques. Journal of Magnetism and Magnetic Materials 320, 7 (2008), 1190--1216.Google Scholar
Cross Ref
- K. Roy. 2013. Approximate computing for energy-efficient error-resilient multimedia systems. In Design and Diagnostics of Electronic Circuits Systems (DDECS), 2013 IEEE 16th International Symposium on. 5--6.Google Scholar
Cross Ref
- Isaac D. Scherson and Sener Ilgen. 1989. A Reconfigurable Fully Parallel Associative Processor. J. Parallel Distrib. Comput. 6, 1 (Feb. 1989), 69--89. Google Scholar
Digital Library
- D. Schinkel, E. Mensink, E. Klumperink, E. van Tuijl, and B. Nauta. 2007. A Double-Tail Latch-Type Voltage Sense Amplifier with 18ps Setup+Hold Time. In 2007 IEEE International Solid-State Circuits Conference. Digest of Technical Papers. 314--605.Google Scholar
- Stelios Sidiroglou-Douskos, Sasa Misailovic, Henry Hoffmann, and Martin Rinard. 2011. Managing Performance vs. Accuracy Trade-offs with Loop Perforation. In Proceedings of the 19th ACM SIGSOFT Symposium and the 13th European Conference on Foundations of Software Engineering (ESEC/FSE’11). ACM, New York, NY, USA, 124--134. Google Scholar
Digital Library
- S. Sinha, G. Yeric, V. Chandra, B. Cline, and Y. Cao. 2012. Exploring sub-20nm FinFET design with Predictive Technology Models. In DAC Design Automation Conference 2012. 283--288. Google Scholar
Digital Library
- Dmitri B. Strukov, Gregory S. Snider, Duncan R. Stewart, and R. Stanley Williams. 2008. The missing memristor found. Nature 453, 7191 (01 May 2008), 80--83.Google Scholar
- GSI Technology. 2017. In-Place Associative Computing. (2017). http://www.gsitechnology.com/node/123377.Google Scholar
- Arizona State University. 2012. Predictive Technology Model (PTM). (2012). http://ptm.asu.edu/.Google Scholar
- S. Venkataramani, A. Sabne, V. Kozhikkottu, K. Roy, and A. Raghunathan. 2012. SALSA: Systematic logic synthesis of approximate circuits. In Design Automation Conference (DAC), 2012 49th ACM/EDAC/IEEE. 796--801. Google Scholar
Digital Library
- C. Yakopcic, T. M. Taha, G. Subramanyam, and R. E. Pino. 2013. Generalized Memristive Device SPICE Model and its Application in Circuit Design. IEEE Transactions on Computer-Aided Design of Integrated Circuits and Systems 32, 8 (Aug 2013), 1201--1214. Google Scholar
Digital Library
- H. E. Yantir, M. E. Fouda, A. M. Eltawil, and F. J. Kurdahi. 2016. Process variations-aware resistive associative processor design. In 2016 IEEE 34th International Conference on Computer Design (ICCD). 49--55.Google Scholar
- L. Yavits, S. Kvatinsky, A. Morad, and R. Ginosar. 2015. Resistive Associative Processor. 14, 2 (July 2015), 148--151. Google Scholar
Digital Library
- L. Yavits, A. Morad, and R. Ginosar. 2015. Computer Architecture with Associative Processor Replacing Last-Level Cache and SIMD Accelerator. IEEE Trans. Comput. 64, 2 (Feb 2015), 368--381.Google Scholar
Digital Library
- A. Yazdanbakhsh, D. Mahajan, H. Esmaeilzadeh, and P. Lotfi-Kamran. 2017. AxBench: A Multiplatform Benchmark Suite for Approximate Computing. IEEE Design Test 34, 2 (April 2017), 60--68.Google Scholar
Cross Ref
- A. Yazdanbakhsh, D. Mahajan, B. Thwaites, J. Park, A. Nagendrakumar, S. Sethuraman, K. Ramkrishnan, N. Ravindran, R. Jariwala, A. Rahimi, H. Esmaeilzadeh, and K. Bazargan. 2015. Axilog: Language support for approximate hardware design. In 2015 Design, Automation Test in Europe Conference Exhibition (DATE). 812--817. Google Scholar
Digital Library
- Amir Yazdanbakhsh, Jongse Park, Hardik Sharma, Pejman Lotfi-Kamran, and Hadi Esmaeilzadeh. 2015. Neural Acceleration for GPU Throughput Processors. In Proceedings of the 48th International Symposium on Microarchitecture (MICRO-48). ACM, New York, NY, USA, 482--493. Google Scholar
Digital Library
Index Terms
Approximate Memristive In-memory Computing
Recommendations
Resistive GP-SIMD Processing-In-Memory
GP-SIMD, a novel hybrid general-purpose SIMD architecture, addresses the challenge of data synchronization by in-memory computing, through combining data storage and massive parallel processing. In this article, we explore a resistive implementation of ...
Threshold Read Method for Multi-bit Memristive Crossbar Memory
ISED '11: Proceedings of the 2011 International Symposium on Electronic System DesignMemristors have raised great interest in various logic and non-volatile memory applications. They are especially a good candidate for crossbar memory applications for their capability of being integrated in high densities and low switching power ...
Memristive voltage divider: a bipolar ReRAM-based unit for non-volatile flip-flops
MEMSYS '17: Proceedings of the International Symposium on Memory SystemsHibernation is the key mechanism for enabling normally-off and transient computing. The speed and energy dissipation of hibernation directly impacts the efficiency of the systems employing such computing paradigms. CMOS-compatible emerging memory ...






Comments