Design and Challenges of Edge Computing ASICs on Front-End Electronics

Miryala, Sandeep; Carini, Gabriella; Deptuch, Grzegorz; Huang, Jin; Katkoori, Srinivas; Maj, Piotr; Mandal, Soumyajit; Ren, Yihui; Zaman, Md Adnan

doi:10.1109/isqed54688.2022.9806248

Title: Design and Challenges of Edge Computing ASICs on Front-End Electronics

Journal Article · Wed Apr 06 00:00:00 EDT 2022 · Proceedings of the IEEE International Symposium on Quality Electronic Design (ISQED)

DOI:https://doi.org/10.1109/isqed54688.2022.9806248· OSTI ID:1906165

Miryala, Sandeep ^[1]; Carini, Gabriella ^[1]; Deptuch, Grzegorz ^[1]; Huang, Jin ^[1]; Katkoori, Srinivas ^[2]; Maj, Piotr ^[1]; Mandal, Soumyajit ^[1]; Ren, Yihui ^[1]; Zaman, Md Adnan ^[1]

Brookhaven National Laboratory (BNL), Upton, NY (United States)
University of South Florida, Tampa, FL (United States)

In situ or hardware-embedded data processing of raw signals, close to their source, in radiation detectors is expected to provide dramatic improvements in data quality and volumes. However, the implementation of artificial neural networks (ANNs) in the front-end electronics, and the design of custom integrated circuits (ASICs), comes with challenges. In addition, detectors have to operate with limited power budget and implement complex functionalities in a very dense space. They often are exposed to extreme conditions as they work in high-radiation environments and/or cryogenic temperatures. This paper presents examples of applications and design methodologies for in-situ ANNs, along with the challenges of retaining the fidelity of the trained networks. For illustration, we use the problem of estimating the energy deposited by the radiation from digitized waveforms. The proposed implementation starts with an ML algorithm trained in Qkeras and eventually leads to an equivalent ASIC implementation. The associated design challenges in realizing energy and area efficient implementations in CMOS processes are reviewed. Novel approaches that employ hybrid technologies (combination of CMOS with memristors), in-memory computing models, and bio-inspired spiking neural networks are also highlighted

View Accepted Manuscript (DOE)

Cite

Export

Save

Research Organization:: Brookhaven National Laboratory (BNL), Upton, NY (United States)

Sponsoring Organization:: USDOE Office of Science (SC), Basic Energy Sciences (BES); USDOE Laboratory Directed Research and Development (LDRD) Program

Grant/Contract Number:: SC0012704

OSTI ID:: 1906165

Report Number(s):: BNL-223813-2022-JAAM

Journal Information:: Proceedings of the IEEE International Symposium on Quality Electronic Design (ISQED), Vol. 2022; Conference: 2022 23. International Symposium on Quality Electronic Design (ISQED), Santa Clara, CA (United States), 6-7 Apr 2022; ISSN 1948-3287

Publisher:: IEEECopyright Statement

Country of Publication:: United States

Language:: English

References (35)

Waveform processing using neural network algorithms on the front-end electronics Miryala, S.; Mittal, S.; Ren, Y. Journal of Instrumentation, Vol. 17, Issue 01 https://doi.org/10.1088/1748-0221/17/01/C01039	journal	January 2022
Extreme Learning Machine for Regression and Multiclass Classification IEEE Transactions on Systems, Man, and Cybernetics, Part B (Cybernetics), Vol. 42, Issue 2 https://doi.org/10.1109/TSMCB.2011.2168604	journal	April 2012
Single Event Upset: An Embedded Tutorial Wang, Fan; Agrawal, Vishwani D. 21st International Conference on VLSI Design (VLSID 2008) https://doi.org/10.1109/VLSI.2008.28	conference	January 2008
A time-over-threshold machine: the readout integrated circuit for the BABAR Silicon Vertex Tracker Kipnis, I.; Collins, T.; DeWitt, J. IEEE Transactions on Nuclear Science, Vol. 44, Issue 3 https://doi.org/10.1109/23.603658	journal	June 1997
A memristor-based long short term memory circuit Smagulova, Kamilya; Krestinskaya, Olga; James, Alex Pappachen Analog Integrated Circuits and Signal Processing, Vol. 95, Issue 3 https://doi.org/10.1007/s10470-018-1180-y	journal	April 2018
CONV-SRAM: An Energy-Efficient SRAM With In-Memory Dot-Product Computation for Low-Power Convolutional Neural Networks Biswas, Avishek; Chandrakasan, Anantha P. IEEE Journal of Solid-State Circuits, Vol. 54, Issue 1 https://doi.org/10.1109/JSSC.2018.2880918	journal	January 2019
Fast inference of deep neural networks in FPGAs for particle physics Duarte, J.; Han, S.; Harris, P. Journal of Instrumentation, Vol. 13, Issue 07 https://doi.org/10.1088/1748-0221/13/07/P07027	journal	July 2018
A Highly Parallel and Energy Efficient Three-Dimensional Multilayer CMOS-RRAM Accelerator for Tensorized Neural Network Huang, Hantao; Ni, Leibin; Wang, Kanwen IEEE Transactions on Nanotechnology, Vol. 17, Issue 4 https://doi.org/10.1109/TNANO.2017.2732698	journal	July 2018
Pixel detectors ... where do we stand? Wermes, N. Nuclear Instruments and Methods in Physics Research Section A: Accelerators, Spectrometers, Detectors and Associated Equipment, Vol. 924 https://doi.org/10.1016/j.nima.2018.07.003	journal	April 2019
An analytical model of the effects of pulse pileup on the energy spectrum recorded by energy resolved photon counting x-ray detectors: Pulse pileup model of photon counting detectors Taguchi, Katsuyuki; Frey, Eric C.; Wang, Xiaolan Medical Physics, Vol. 37, Issue 8 https://doi.org/10.1118/1.3429056	journal	July 2010
UNPU: An Energy-Efficient Deep Neural Network Accelerator With Fully Variable Weight Bit Precision Lee, Jinmook; Kim, Changhyeon; Kang, Sanghoon IEEE Journal of Solid-State Circuits, Vol. 54, Issue 1 https://doi.org/10.1109/JSSC.2018.2865489	journal	January 2019
The deconvolution method of fast pulse shaping at hadron colliders Gadomski, S.; Hall, G.; Høgh, T. Nuclear Instruments and Methods in Physics Research Section A: Accelerators, Spectrometers, Detectors and Associated Equipment, Vol. 320, Issue 1-2 https://doi.org/10.1016/0168-9002(92)90779-4	journal	August 1992
Neuromorphic computing: From devices to integrated circuits Saxena, Vishal Journal of Vacuum Science & Technology B, Vol. 39, Issue 1 https://doi.org/10.1116/6.0000591	journal	January 2021
Optimization of Switching Metrics for CMOS Integrated HfO2 based RRAM Devices on 300 mm Wafer Platform Hazra, Jubin; Liehr, Maximilian; Beckmann, Karsten 2021 IEEE International Memory Workshop (IMW) https://doi.org/10.1109/IMW51353.2021.9439618	conference	May 2021
A novel non-linear recursive filter design for extracting high rate pulse features in nuclear medicine imaging and spectroscopy Sajedi, Salar; Kamal Asl, Alireza; Ay, Mohammad R. Medical Engineering & Physics, Vol. 35, Issue 6 https://doi.org/10.1016/j.medengphy.2012.08.003	journal	June 2013
Super-resolution for x-ray applications with pixelated semiconductor tracking detectors using convolutional neural networks Eckert, Björn; Aschauer, Stefan; Holl, Peter Software and Cyberinfrastructure for Astronomy VI https://doi.org/10.1117/12.2576067	conference	December 2020
Memristors Empower Spiking Neurons With Stochasticity Al-Shedivat, Maruan; Naous, Rawan; Cauwenberghs, Gert IEEE Journal on Emerging and Selected Topics in Circuits and Systems, Vol. 5, Issue 2 https://doi.org/10.1109/JETCAS.2015.2435512	journal	June 2015
Equivalent Noise Charge of Monolithic Active Pixel Sensors for Use in Charged Particle Detection Fourches, Nicolas T. IEEE Transactions on Nuclear Science, Vol. 56, Issue 4 https://doi.org/10.1109/TNS.2009.2024942	journal	August 2009
Memristor-The missing circuit element Chua, L. IEEE Transactions on Circuit Theory, Vol. 18, Issue 5 https://doi.org/10.1109/TCT.1971.1083337	journal	January 1971
Artificial intelligence called in to tackle LHC data deluge Castelvecchi, Davide Nature, Vol. 528, Issue 7580 https://doi.org/10.1038/528018a	journal	December 2015
Multiply accumulate operations in memristor crossbar arrays for analog computing Chen, Jia; Li, Jiancong; Li, Yi Journal of Semiconductors, Vol. 42, Issue 1 https://doi.org/10.1088/1674-4926/42/1/013104	journal	January 2021
Coincidence Counters for Charge Sharing Compensation in Spectroscopic Photon Counting Detectors Hsieh, Scott S. IEEE Transactions on Medical Imaging, Vol. 39, Issue 3 https://doi.org/10.1109/TMI.2019.2933986	journal	March 2020
Spiking Neural Networks and online learning: An overview and perspectives Lobo, Jesus L.; Del Ser, Javier; Bifet, Albert Neural Networks, Vol. 121 https://doi.org/10.1016/j.neunet.2019.09.004	journal	January 2020
Free-electron-laser-based biophysical and biomedical instrumentation Edwards, G. S.; Austin, R. H.; Carroll, F. E. Review of Scientific Instruments, Vol. 74, Issue 7 https://doi.org/10.1063/1.1584078	journal	July 2003
VMM1—An ASIC for Micropattern Detectors De Geronimo, G.; Fried, J. IEEE Transactions on Nuclear Science, Vol. 60, Issue 3 https://doi.org/10.1109/TNS.2013.2258683	journal	June 2013
Future trends in synchrotron science at NSLS-II Hill, John; Campbell, Stuart; Carini, Gabriella Journal of Physics: Condensed Matter, Vol. 32, Issue 37 https://doi.org/10.1088/1361-648X/ab7b19	journal	June 2020
CHIMERA: A 0.92 TOPS, 2.2 TOPS/W Edge AI Accelerator with 2 MByte On-Chip Foundry Resistive RAM for Efficient Training and Inference Giordano, Massimo; Prabhu, Kartik; Koul, Kalhan 2021 Symposium on VLSI Circuits https://doi.org/10.23919/VLSICircuits52068.2021.9492347	conference	June 2021
MAGIC—Memristor-Aided Logic Kvatinsky, Shahar; Belousov, Dmitry; Liman, Slavik IEEE Transactions on Circuits and Systems II: Express Briefs, Vol. 61, Issue 11 https://doi.org/10.1109/TCSII.2014.2357292	journal	November 2014
Effects of Bias and Temperature on the Dose-Rate Sensitivity of 65-nm CMOS Transistors Borghello, Giulio; Faccio, Federico; Termo, Gennaro IEEE Transactions on Nuclear Science, Vol. 68, Issue 5 https://doi.org/10.1109/TNS.2021.3062622	journal	May 2021
TDSNN: From Deep Neural Networks to Deep Spike Neural Networks with Temporal-Coding Zhang, Lei; Zhou, Shengyuan; Zhi, Tian Proceedings of the AAAI Conference on Artificial Intelligence, Vol. 33, Issue 01 https://doi.org/10.1609/aaai.v33i01.33011319	journal	July 2019
Shaper Design in CMOS for High Dynamic Range De Geronimo, Gianluigi; Li, Shaorui IEEE Transactions on Nuclear Science, Vol. 58, Issue 5 https://doi.org/10.1109/TNS.2011.2162963	journal	October 2011
LHC Machine Evans, Lyndon; Bryant, Philip Journal of Instrumentation, Vol. 3, Issue 08 https://doi.org/10.1088/1748-0221/3/08/S08001	journal	August 2008
Machine Learning in High Energy Physics Community White Paper Albertsson, Kim; Altoe, Piero; Anderson, Dustin Journal of Physics: Conference Series, Vol. 1085 https://doi.org/10.1088/1742-6596/1085/2/022008	journal	September 2018
A Reconfigurable Neural Network ASIC for Detector Front-End Data Compression at the HL-LHC Guglielmo, Giuseppe Di; Fahim, Farah; Herwig, Christian IEEE Transactions on Nuclear Science, Vol. 68, Issue 8 https://doi.org/10.1109/TNS.2021.3087100	journal	August 2021
Real-time data processing in the ALICE High Level Trigger at the LHC Computer Physics Communications, Vol. 242, p. 25-48 https://doi.org/10.1016/j.cpc.2019.04.011	journal	September 2019

Similar Records

A Reconfigurable Neural Network ASIC for Detector Front-End Data Compression at the HL-LHC

Journal Article · Sun Aug 01 00:00:00 EDT 2021 · IEEE Transactions on Nuclear Science · OSTI ID:1906165

Di Guglielmo, Giuseppe; Fahim, Farah; Herwig, Christian; +15 more

A Hardware and Software Co-design Framework for Energy Efficient Neuromorphic Systems

Technical Report · Wed Jul 05 00:00:00 EDT 2023 · OSTI ID:1906165

Li, Hai; Taylor, Brady

Design and Measurement of a Low-Noise 64-Channels Front-End Readout ASIC for CdZnTe Detectors

Conference · Wed Jul 01 00:00:00 EDT 2015 · OSTI ID:1906165

Gan, Bo; Wei, Tingcun; Gao, Wu; +2 more

Related Subjects

47 OTHER INSTRUMENTATION
AI/ML
ANN
front-end electronics
ASIC
edge computing
memristors

Title: Design and Challenges of Edge Computing ASICs on Front-End Electronics

Citation Formats

References (35)

Similar Records

Related Subjects