research-article

Public Access

Using branch predictors to predict brain activity in brain-machine implants

Author:

Abhishek BhattacharjeeAuthors Info & Claims

MICRO-50 '17: Proceedings of the 50th Annual IEEE/ACM International Symposium on Microarchitecture

Pages 409 - 422

https://doi.org/10.1145/3123939.3123943

Published: 14 October 2017 Publication History

Abstract

A key problem with implantable brain-machine interfaces is that they need extreme energy efficiency. One way of lowering energy consumption is to use the low power modes available on the processors embedded in these devices. We present a technique to predict when neuronal activity of interest is likely to occur so that the processor can run at nominal operating frequency at those times, and be placed in low power modes otherwise. To achieve this, we discover that branch predictors can also predict brain activity. We perform brain surgeries on awake and anesthetized mice, and evaluate the ability of several branch predictors to predict neuronal activity in the cerebellum. We find that perceptron branch predictors can predict cerebellar activity with accuracies as high as 85%. Consequently, we co-opt branch predictors to dictate when to transition between low power and normal operating modes, saving as much as 59% of processor energy.

References

[1]

{n. d.}. Cerebellum Image. Life Science Databases/Wikimedia Commons ({n. d.}).

[2]

{n. d.}. Utah array. http://churchlandlab.neuroscience.columbia.edu/images/utahArray.jpg ({n. d.}).

[3]

{n. d.}. Utah array plugged. http://prometheus.med.utah.edu/bwjones/wp-content/uploads/iblog/Implant1.jpg ({n. d.}).

[4]

Manor Alwani, Han Chen, Michael Ferdman, and Peter Milner. 2016. Fused-Layer CNN Accelerators. Int'l Symp. on Microarch. (2016).

[5]

Renee St. Amant, Daniel Jimenez, and Doug Burger. 2008. Low-Power, High-Perf. Analog Neural Branch Prediction. Int'l Symp. on Microarch. (2008).

Digital Library

[6]

Gian Nicola Angotzi, Fabio Boi, Stefano Zordan, Andrea Bonfanti, and Alessandro Vato. 2014. A Programmable Closed-Loop Recording and Stimulating Wireless System for Behaving Small Laboratory Animals. Scie. Reps. 4, 5963 (2014).

[7]

M Aravind and Suresh Babu. 2015. Embedded Implementation of Brain Comp. Interface Concept Using FPGA. Int'l Jnl. of Science and Research (2015).

[8]

Amirali Baniasadi and Andreas Moshovos. 2002. Branch Predictor Prediction: A Power-Aware Branch Predictor for High-Perf. Processors. ICCD (2002).

[9]

Boris Barbour. {n. d.}. Equipe Cervelet. http://www.ibens.ens.fr ({n. d.}).

[10]

Abhishek Bhattacharjee and Margaret Martonosi. 2009. Thread Criticality Predictors for Dynamic Perf., Power, and Resource Management in Chip Multiprocessors. Int'l Symp. on Comp. Arch. (2009).

Digital Library

[11]

Michael Bielawski and Helen Bondurant. 2015. Psychosis Following a Stroke to the Cerebellum and Midbrain: A Case Report. Cerebellum and Ataxias (2015).

[12]

Yunji Chen, Tao Luo, Shaoli Liu, Shijin Zhang, Liqiang He, Jia Wang, Ling Li, Tianshi Chen, Zhiwei Xu, Ninghui Sun, and Olivier Temam. 2014. DaDianNao: A Machine-Learning Supercomputer. Int'l Symp. on Microarch. (2014).

Digital Library

[13]

Yu-Hsin Chen, Tushar Krishna, Joel Emer, and Vivienne Sze. 2016. 14.5 Eyeriss: An Energy-Efficient Reconfigurable Accelerator for Deep Convolutional Neural Networks. Int'l Solid State Circuits Conf. (2016).

[14]

Steven Cooreman. 2016. Power-Saving Tips When Rapid Prototyping ARM Cortex-M MCUs. http://electronicdesign.com/power/power-saving-tips-when-rapid-prototyping-arm-cortex-m-mcus (2016).

[15]

Qingyuan Deng, David Meisner, Abhishek Bhattacharjee, Thomas Wenisch, and Ricardo Bianchini. 2012. CoScale: Coordinating CPU and Memory SystemDVFS in Server Sys. Int'l Symp. on Microarch. (2012).

Digital Library

[16]

Qingyuan Deng, David Meisner, Abhishek Bhattacharjee, Thomas Wenisch, and Ricardo Bianchini. 2012. MultiScale: Memory System DVFS with Multiple Memory Controllers. Int'l Symp. on Low Power Elec. and Des. (2012).

Digital Library

[17]

Qingyuan Deng, David Meisner, Luis Ramos, Thomas Wenisch, and Ricardo Bianchini. 2011. MemScale: Active Low-Power Modes for Main Memory. Int'l Conf. on Arch. Supp. for Prog. Lang. and Op. Sys. (2011).

Digital Library

[18]

Alessandro Stamatto Ferreira, Leonardo Cunha de Miranda, Erica Cunha de Miranda, and Sarah Gomes Sakamoto. 2013. A Survey of Interactive Sys. Based on Brain-Comp. Interfaces. SBC Jnl. on 3D Interactive Sys. 4, 1 (2013).

[19]

Volker Gauck and Dieter Jaeger. 2000. The Control of Rate and Timing of Spikes in the Deep Cerebellar Nuclei by Inhibition. Jnl. of Neuro. 20, 8 (2000).

[20]

Bernhard Graimann, Brendan Allison, and Gert Pfurtscheller. 2010. Brain-Comp. Interfaces: A Gentle Introduction. The Frontiers Collection (2010).

[21]

Atif Hashmi, Hugues Berry, Olivier Temam, and Mikko Lipasti. 2008. Automatic Abstraction and Fault Tolerance in Cortical Microarch.s. Int'l Symp. on Comp. Arch. (2008).

Digital Library

[22]

S Herbert and D Marculescu. 2007. Analysis of Dynamic Voltage/Frequency Scaling in Chip Multiprocessors. Int'l Symp. on Low Power Elec. and Des. (2007).

Digital Library

[23]

Masayuki Hirata, Kojiro Matsushita, Takafumi Suzuki, Takeshi Yoshida, Fumihiro Sato, Shayne Morris, Takufumi Yanagisawa, Tetsu Goto, Mitsuo Kawato, and Toshiki Yoshimine. 2014. A Fully-Implantable Wireless System for Human Brain-Machine Interfaces Using Brain Surface Electrodes: W-HERBS. IEEE Trans. on Comm. E94-B, 9 (2014).

[24]

Daniel Jimenez. 2003. Fast Path-Based Neural Branch Prediction. Int'l Symp. on Comp. Arch. (2003).

Digital Library

[25]

Daniel Jimenez. 2005. Piecewise Linear Branch Prediction. Int'l Symp. on Comp. Arch. (2005).

Digital Library

[26]

Daniel Jimenez and Calvin Lin. 2001. Dynamic Branch Prediction with Perceptrons. Int'l Symp. on High Perf. Comp. Arch. (2001).

Digital Library

[27]

Daniel Jimenez and Calvin Lin. 2002. Neural Methods for Dynamic Branch Prediction. ACM Trans. on Arch. and Code Optimization (2002).

[28]

Alok Joshi, Vahab Youssofzadeh, Vinith Vemana, T McGinnity, Girijesh Prasad, and KongFatt Wong-Lin. 2017. An Integrated Modelling Framework for Neural Circuits with Multiple Neuromodulators. Jnl. of the Royal Soc. Interface (2017).

[29]

G Kaloshi, V Alikaj, A Rroji, G Vreto, and M Petrela. 2013. Visual and Auditory Hallucinations Revealing Cerebellar Extraventricular Neurocytoma: Uncommon Presentation for Uncommon Tumor in Uncommon Location. General Hostpial Psychiatry 35, 6 (2013).

[30]

Stefanos Kaxiras and Margaret Martonosi. 2009. Comp. Arch. Techniques for Power Efficiency. Synthesis Lecture Series (2009).

Digital Library

[31]

Ryan Kelly, Matthew Smith, Jason Samonds, Adam Kohn, A Bonds, J Movshon, and Tai Lee. 2007. Comparison of Recordings from Microelectrode Arrays and Single Electrodes in the Visual Cortex. Jnl. of Neuro. 27, 2 (2007).

[32]

P Kohler, C Linsmeier, J Thelin, M Bengtsson, H Jorntell, M Garwicz, J Schouenborg, and L Wallman. 2009. Flexible Multi-Electrode Brain-Machine Interface for Recording in the Cerebellum. IEEE Eng. Medicine Biology Soc. 536, 8 (2009).

[33]

Ki Yong Kwon, Seif Eldawatly, and Karim Oweiss. 2012. NeuroQuest: A Comprehensive Analysis Tool for Extracellular Neural Ensemble Recording. Jnl. of Neuro. Methods 204, 1 (2012).

[34]

Charles Lefurgy, Kartik Rajamani, F Rawson, W Felter, M Kistler, and T Keller. 2003. Energy Management for Commercial Servers. IEEE Comp. 36, 12 (2003).

Digital Library

[35]

Jian Li, Jose Martinez, and Michael Huang. 2004. The Thrifty Barrier: Energy-Aware Synchronization in Shared-Memory Multiprocessors. Int'l Symp. on High Perf. Comp. Arch. (2004).

Digital Library

[36]

Sheng Li, Jung Ho Ahn, Richard Strong, Jay Brockman, Dean Tullsen, and Norman Jouppi. 2009. McPAT: An Integrated Power, Area, and Timing Modeling Framework for Multicore and Manycore Arch.s. Int'l Symp. on Microarch. (2009).

Digital Library

[37]

Daofu Liu, Tianshi Chen, Shaoli Liu, Jinhong Zhou, Shengyuan Zhou, Olivier Temam, Xiaobing Feng, Xuehai Zhou, and Yunji Chen. 2015. Pudiannao: A Polyvalent Machine Learning Accelerator. Int'l Conf. on Arch. Supp. for Prog. Lang. and Op. Sys. (2015).

Digital Library

[38]

Xilin Liu, Basheer Subei, Milin Zhang, Andrew Richardson, Timothy Lucas, and Jan Van der Spiegel. 2014. The PennBMBI: A General Purpose Wireless Brain-Machine-Brain Interface System for Unrestrained Animals. IEEE Int'l Symp. on Circuits and Sys. (2014).

[39]

N Matsumi, K Matsumoto, N Mishima, E Moriyama, T Furuta, A Nishimoto, and K Taguchi. 1993. Thermal Damage Threshold of Brain Tissue - Histological Study of Heated Normal Monkey Brains. Neurol Med Chir (1993).

[40]

Scott McFarling. 1993. Combining Branch Predictors. Tech. Rep. TN-36m, Digital Western Lab (1993).

[41]

David Meisner, Brian Gold, and Thomas Wenisch. 2009. PowerNap: Eliminating Server Idle Power. Int'l Conf. on Arch. Supp. for Prog. Lang. and Op. Sys. (2009).

Digital Library

[42]

David Meisner, Christopher Sadler, Luis Barroso, W-D Webber, and Thomas Wenisch. 2011. Power Management of On-Line Data Intensive Services. Int'l Symp. on Comp. Arch. (2011).

Digital Library

[43]

David Meisner and Thomas Wenisch. 2012. DreamWeaver: Arch. Supp. for Deep Sleep. Int'l Conf. on Arch. Supp. for Prog. Lang. and Op. Sys. (2012).

Digital Library

[44]

Jorge Mercado, Javier Herrera, Arturo de Jesus Plansza, and Josefina Guiterrez. 2016. Embedded EEG Recording Module with Active Electrodes for Motor Imagery Brain-Comp. Interface. IEEE Latin America Trans. 75 (2016).

[45]

Corinne Mestais, Guillaume Charvet, Fabien Sauter-Starace, Michael Foerster, David Ratel, and Alim Louis Bernabid. 2014. WIMAGINE: Wireless 64-Channel ECoG Recording Implant for Long Term Clinical Applications. IEEE Trans. on Neural Sys. and Rehab. Eng. 23, 1 (2014).

[46]

Gregory Mone. 2015. Sens. on the Brain. Comm. of the ACM 60, 4 (2015).

Digital Library

[47]

Christian Muhl, Brendan Allison, Anton Nijholt, and Guillaume Chanel. 2014. A Survey of Affective Brain Comp. Interfaces: Principles, State-of-the-Art, and Challenges. Brain-Comp. Interfaces 1, 2 (2014).

[48]

Naveen Muralimanohar, Rajeev Balasubramonian, and Norman Jouppi. 2007. CACTI 6.0: A Tool to Model Large Caches. Int'l Symp. on Microarch. (2007).

[49]

Andrew Nere, Atif Hashmi, Mikko Lipasti, and Giulio Tononi. 2013. Bridging the Semantic Gap: Emulating Biological Neuronal Behavior with Simple Digital Neurons. Int'l Symp. on High Perf. Comp. Arch. (2013).

Digital Library

[50]

TKT Nguyen, Zaneta Navratilova, Henrique Cabral, Ling Wang, Georges Gielen, FP Battaglia, and Carmen Bartic. 2014. Closed-Loop Optical Neural Stimulation Based on a 32-Channel Low-Noise Recording System with Online Spike Sorting. Jnl. of Neural Eng. 11, 4 (2014).

[51]

C Nordhausen, E Maynard, and R Normann. 1996. Single Unit Recording Capabilities of a 100 Microelectrode Array. Brain Res (1996).

[52]

Open Ephys Wiki. 2015. Possible Projects and Future Development. https://open-ephys.atlassian.net/wiki/ (2015).

[53]

Ilker Ozden, Megan Sullivan, Megan Lee, and Samuel Wang. 2009. Reliable Coding Emerges from Coactivation of Climbing Fibers in Microbands of Cerebellar Purkinje Neurons. Jnl. of Neuro. 29, 34 (2009).

[54]

A Palumbo, F Amato, B Calabrese, M Cannataro, G Cocorullo, A Gambardella, P Guzzi, M Lanuzza, M Sturniolo, P Veltri, and P Vizza. 2015. An Embedded System for EEG Acquisition and Processing for Brain Comp. Interface Applications. Wearable and Autonomous Bio. Dev. and Sys. for Smart Environments 75 (2015).

[55]

Dharmesh Parikh, Kevin Skadron, Yan Zhang, Marco Barcella, and Mircea Stan. 2002. Power Issues Related to Branch Prediction. HPCA (2002).

Digital Library

[56]

Hernan Picard, Isabelle Amado, Sabine Mouchet-Mages, Jean-Pierre Olie, and Marie-Odile Krebs. 2008. The Role of the Cerebellum in Schizophrenia: An Update of Clinical, Cognitive, and Functional Evidences. Schizo. Bull. 34, 1 (2008).

[57]

Steve Ramirez, Xu Liu, Pei-Ann Lin, Junghyup Suh, Michael Pignatelli, Roger Redondo, Tomas Ryan, and Susomo Tonegawa. 2013. Creating a False Memory in the Hippocampus. Science 341, 6144 (2013).

[58]

Hernan Rey, Carlos Padreira, and Rodrigo Quiroga. 2015. Past, Present, and Future of Spike Sorting Techniques. Elsevier Review (2015).

[59]

B Rosin, M Slovik, R Mitelman, M Rivlin-Etzion, S Haber, Z Israel, E Vaadia, and H Bergman. 2011. Closed-Loop Deep Brain Stimulation is Superior in Ameliorating Parkinsioniasm. Neuron 72, 2 (2011).

[60]

James Smith. 1981. A Study of Branch Prediction Strategies. Int'l Symp. on Comp. Arch. (1981).

Digital Library

[61]

James Smith. 2014. Efficient Digital Neurons for Larce Scale Cortical Arch.s. Int'l Symp. on Comp. Arch. (2014).

Digital Library

[62]

ST Microelectronics. 2016. Ultra-low-power ARM Cortex-M4 32-bit datasheet. http://www.st.com/content/ccc/resource/technical/document/datasheet/ (2016).

[63]

Ian Stevenson and Konrad Kording. 2011. How Advances in Neural Recording Affect Data Analysis. Nature Neuro. 14 (2011).

[64]

Yi Su, Sudhamayee Routhu, Kee Moon, Sung Lee, WooSub Youm, and Yusuf Ozturk. 2016. A Wireless 32-Channel Implantable Bidirectional Brain Machine Interface. Sens. 16, 1582 (2016).

[65]

M Sullivan, A Nimmerjahn, D Sarkisov, F Helmchen, and SS-H Wang. 2005. In Vivo Calcium Imaging of Circuit Activity in Cerebellar Cortex. Jnl. of Neurophys. 94 (2005).

[66]

S Suner, M Fellows, C Vargas-Irwin, G Nakata, and J Donoghue. 2005. Reliability of Signals From a Chronically Implanted, Silicon-Based Electrode Array in Non-Human Primate Primary Motor Cortex. IEEE Trans. on Neural Sys. and Rehab. Eng. (2005).

[67]

D Tank, M Sugimori, J Connor, and R Llinas. 1998. Spatially Resolved Calcium Dynamics of Mammalian Purkinje Cells in Cerebellar Slice. Science 242 (1998).

[68]

Elvira Teran, Zhe Wang, and Daniel Jimenez. 2016. Perceptron Learning for Reuse Prediction. Int'l Symp. on Microarch. (2016).

[69]

Patrick Wolf. 2008. Thermal Considerations for the Des. of an Implanted Cortical Brain-Machine Interface (BMI). Indwelling Neural Implants: Strategies for Contending with the In Vivo Environment (2008).

[70]

Pavel Yarmolenko, Eui Jung Moon, Chelsea Landon, Ashley Manzoor, Daryl Hochman, Benjamin Viglianti, and Mark Dewhirst. 2013. Thresholds for Thermal Damage to Normal Tissue: An Update. Int'l Jnl. of Hyperthermia (2013).

[71]

Tse-Yu Yeh and Yale Patt. 1991. Two-Level Adaptive Training Branch Prediction. Int'l Symp. on Microarch. (1991).

Digital Library

[72]

Stavros Zanos, Andrew Richardson, Larry Shupe, Frank Miles, and Eberhard Fetz. 2011. The Neurochip-2: An Autonomous Head-Fixed Comp. for Recording and Stimulating in Freely Behaving Monkeys. IEEE Trans. on Neural Sys. and Rehab. Eng. 19, 4 (2011).

[73]

C De Zeeuw, J Simpson, C Hoogenraad, N Galjart, S Koekkoek, and T Ruigrok. 1998. Microcircuitry and the Function of the Inferior Olive. Trends in Neuro. 21, 9 (1998).

Cited By

Lee DLee GKwon DLee SKim YKim J(2018)FlexonProceedings of the 45th Annual International Symposium on Computer Architecture10.1109/ISCA.2018.00032(275-288)Online publication date: 2-Jun-2018
https://dl.acm.org/doi/10.1109/ISCA.2018.00032
Richter EValancius SMcclanahan JMixter JAkoglu A(2018)Balancing the learning ability and memory demand of a perceptron-based dynamically trainable neural networkThe Journal of Supercomputing10.1007/s11227-018-2374-x74:7(3211-3235)Online publication date: 1-Jul-2018
https://dl.acm.org/doi/10.1007/s11227-018-2374-x
Mittal S(2018)A survey of techniques for dynamic branch predictionConcurrency and Computation: Practice and Experience10.1002/cpe.466631:1Online publication date: 2-Sep-2018
https://doi.org/10.1002/cpe.4666

Index Terms

Using branch predictors to predict brain activity in brain-machine implants
1. Computer systems organization
2. Hardware
  1. Emerging technologies
    1. Biology-related information processing
      1. Bio-embedded electronics
      2. Neural systems

Recommendations

Power and frequency analysis for data and control independence in embedded processors
IGCC '11: Proceedings of the 2011 International Green Computing Conference and Workshops

In this work we study control independence in embedded processors. We classify control independent instructions to data dependent and data independent and measure each group's frequency and behavior. Moreover, we study how control independent ...
Power Issues Related to Branch Prediction
HPCA '02: Proceedings of the 8th International Symposium on High-Performance Computer Architecture

This paper explores the role of branch predictor organization in power/energy/performance tradeoffs for processor design. We find that as a general rule, to reduce overall energy consumption in the processor it is worthwhile to spend more power in the ...
Power-Aware Branch Prediction: Characterization and Design

Abstract--This paper uses Wattch and the SPEC 2000 integer and floating-point benchmarks to explore the role of branch predictor organization in power/energy/performance trade offs for processor design. Even though the direction predictor by itself ...

Comments

Please enable JavaScript to view thecomments powered by Disqus.

Information & Contributors

Information

Published In

cover image ACM Conferences

MICRO-50 '17: Proceedings of the 50th Annual IEEE/ACM International Symposium on Microarchitecture

October 2017

850 pages

ISBN:9781450349529

DOI:10.1145/3123939

General Chairs:
Hillery Hunter
IBM Research
,
Jaime Moreno
IBM Research
,
Program Chairs:
Joel Emer
NVIDIA and MIT
,
Daniel Sanchez
MIT

Copyright © 2017 ACM.

Permission to make digital or hard copies of all or part of this work for personal or classroom use is granted without fee provided that copies are not made or distributed for profit or commercial advantage and that copies bear this notice and the full citation on the first page. Copyrights for components of this work owned by others than ACM must be honored. Abstracting with credit is permitted. To copy otherwise, or republish, to post on servers or to redistribute to lists, requires prior specific permission and/or a fee. Request permissions from [email protected]

Sponsors

SIGMICRO: ACM Special Interest Group on Microarchitectural Research and Processing
IEEE-CS\DATC: IEEE Computer Society

Publisher

Association for Computing Machinery

New York, NY, United States

Publication History

Published: 14 October 2017

Permissions

Request permissions for this article.

Request Permissions

Check for updates

Author Tags

Qualifiers

Research-article

Funding Sources

NSF

Conference

MICRO-50

Sponsor:

SIGMICRO
IEEE-CS\DATC

MICRO-50: The 50th Annual IEEE/ACM International Symposium on Microarchitecture

October 14 - 18, 2017

Massachusetts, Cambridge

Acceptance Rates

Overall Acceptance Rate 484 of 2,242 submissions, 22%

Contributors

Other Metrics

View Article Metrics

Bibliometrics & Citations

Bibliometrics

Article Metrics

3
Total Citations
View Citations
585
Total Downloads

Downloads (Last 12 months)66
Downloads (Last 6 weeks)10

Reflects downloads up to 26 Nov 2024

Other Metrics

View Author Metrics

Citations

Cited By

Lee DLee GKwon DLee SKim YKim J(2018)FlexonProceedings of the 45th Annual International Symposium on Computer Architecture10.1109/ISCA.2018.00032(275-288)Online publication date: 2-Jun-2018
https://dl.acm.org/doi/10.1109/ISCA.2018.00032
Richter EValancius SMcclanahan JMixter JAkoglu A(2018)Balancing the learning ability and memory demand of a perceptron-based dynamically trainable neural networkThe Journal of Supercomputing10.1007/s11227-018-2374-x74:7(3211-3235)Online publication date: 1-Jul-2018
https://dl.acm.org/doi/10.1007/s11227-018-2374-x
Mittal S(2018)A survey of techniques for dynamic branch predictionConcurrency and Computation: Practice and Experience10.1002/cpe.466631:1Online publication date: 2-Sep-2018
https://doi.org/10.1002/cpe.4666

View Options

View options

PDF

View or Download as a PDF file.

eReader

View online with eReader.

Login options

Check if you have access through your login credentials or your institution to get full access on this article.

Full Access

Get this Publication

Media

Figures

Other

Tables

View Table of Contents