Tim Zhang, A. Amirsoleimani, J. Eshraghian, M. Azghadi, R. Genov, Yu Xia
{"title":"SSCAE: A Neuromorphic SNN Autoencoder for sc-RNA-seq Dimensionality Reduction","authors":"Tim Zhang, A. Amirsoleimani, J. Eshraghian, M. Azghadi, R. Genov, Yu Xia","doi":"10.1109/ISCAS46773.2023.10181994","DOIUrl":"https://doi.org/10.1109/ISCAS46773.2023.10181994","url":null,"abstract":"Single-cell RNA sequencing is an emerging technique in the field of biology that departs radically from the previous assumption of gene-expression homogeneity within a tissue. The large quantity of data generated by this technology enables discoveries of cellular biology and disease mechanics that were previously not possible, and calls for accurate, scalable, and efficient processing pipelines. In this work, we propose SSCAE (spiking single-cell autoencoder), a novel SNN-based autoencoder for sc-RNA-seq dimensionality reduction. We apply this architecture to a variety of datasets, and the results show that it can match and surpass the performance of current state-of-the-art techniques. Moreover, the potential of this technique lies in its ability to be scaled up and to take advantage of neuromorphic hardware, circumventing the memory bottleneck that currently limits the size of sequencing datasets that can be processed.","PeriodicalId":177320,"journal":{"name":"2023 IEEE International Symposium on Circuits and Systems (ISCAS)","volume":"12 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-05-21","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"127911416","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
{"title":"A 0.98 pJ/Cycle 3.7 ppm Long-Term Stability Frequency-Locked Oscillator with Switched-Capacitor and Switched-Resistor Techniques","authors":"Yun-Sheng Hsieh, Bo Li, Kuang-Wei Cheng","doi":"10.1109/ISCAS46773.2023.10182024","DOIUrl":"https://doi.org/10.1109/ISCAS46773.2023.10182024","url":null,"abstract":"This work presents an energy-efficient on-chip resistive frequency-locked oscillator (RFLO) for achieving superb temperature and frequency stabilities. The resistive frequency-locked oscillator outperforms the power consumption and the temperature coefficient (TC) compared to the conventional relaxation oscillator. Frequency dividers are utilized in the feedback loop to reduce the reference current and clock power consumption. Moreover, switched-capacitor and switched-resistor techniques are both exploited to accomplish low area and low power consumption. This work was fabricated in TSMC $0.180 mumathrm{m}$ process. The prototype operates at 200 kHz and achieves a 23.5 ppm/°C of TC across the temperature range from −40°C to 90°C and a line sensitivity of 0.44 %/V. Consuming 196 nW at 1 V supply voltage, it can reach a 0.98 pJ/cycle of energy efficiency.","PeriodicalId":177320,"journal":{"name":"2023 IEEE International Symposium on Circuits and Systems (ISCAS)","volume":"12 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-05-21","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"131384355","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
{"title":"IVATS: A Leakage Reduction Technique Based on Input Vector Analysis and Transistor Stacking in CMOS Circuits","authors":"Lishuo Deng, Keran Li, Weiwei Shan","doi":"10.1109/ISCAS46773.2023.10182138","DOIUrl":"https://doi.org/10.1109/ISCAS46773.2023.10182138","url":null,"abstract":"Leakage reduction is crucial for always-on IoT applications in which static power consumption of the memory cells accounts for a large proportion of the total power. Even with high threshold voltage transistors, the leakage is still considerable. This paper proposes a novel technique based on input vector analysis and transistor stacking to analyze and suppress leakage, especially for extremely high threshold voltage (EHVT) circuits operating in the near/sub-threshold regime. At the device level, we consider the leakage ratio of each transistor terminal, which improves the universality of the method. At the circuit level, we innovatively propose the concepts of critical leakage path, leakage power components, and public leakage path to help designers locate the sources of leakage more precisely. We apply the method to a 28nm-EHVT low leakage tristate latch-like memory cell in a serial Fast Fourier Transform (FFT) circuit and find that inserting one stacking NMOS and using “01” stack to reduce the substrate leakage of PMOS can effectively suppress leakage. The average leakage power consumption of the optimized cell is reduced by 42% in the pre-layout simulation. A 26.87% and 17.52% leakage power reduction in the custom cell and the serial FFT circuit is achieved after the layout design and the synthesis.","PeriodicalId":177320,"journal":{"name":"2023 IEEE International Symposium on Circuits and Systems (ISCAS)","volume":"53 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-05-21","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"132252405","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
{"title":"Fast VVC Intra Encoding for Video Coding for Machines","authors":"Aorui Gou, Heming Sun, Xiaoyang Zeng, Yibo Fan","doi":"10.1109/ISCAS46773.2023.10181507","DOIUrl":"https://doi.org/10.1109/ISCAS46773.2023.10181507","url":null,"abstract":"Traditional video coding technologies compress and reconstruct the video frames, which focus on human perception. However, video coding for machines (VCM) uses the feature stream to bridge the correlation between human perception and machine intelligence for vision tasks. We extract the features for the CU with different shapes with part of resnet architecture for VCM. However, the feature-based methods use the model to complete the forward process, which is very time-consuming for its complex architecture and parameter size. The CU architecture for the feature extraction further increases the operation times. A fast algorithm based on the Histogram of oriented gradient (H OG) is proposed for the video coding for machines with VVC intra to overcome the time-consuming problems while maintaining the performance for the vision tasks with codec. The correlation of the mode decision with the VCM performance is discussed to motivate the fast intra coding for V CM. Moreover, the VTM and VVenc are used to verify the universality of the proposed method. The proposed methods can speed up the fast encoding for 35.21 % time saving with 0.26 increment for AP50 for the cityscapes dataset compared with the VTM10.0.","PeriodicalId":177320,"journal":{"name":"2023 IEEE International Symposium on Circuits and Systems (ISCAS)","volume":"15 12","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-05-21","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"132335912","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Sara Alahmadi, Haytham Idriss, P. Rojas, M. Bayoumi
{"title":"Security Scalability of Arbiter PUF Designs","authors":"Sara Alahmadi, Haytham Idriss, P. Rojas, M. Bayoumi","doi":"10.1109/ISCAS46773.2023.10181541","DOIUrl":"https://doi.org/10.1109/ISCAS46773.2023.10181541","url":null,"abstract":"Physically Unclonable Functions (PUFs) are hardware security primitives that can offer an alternative lightweight security solution for authenticating constrained Internet of Things (IoT) devices. However, PUFs are susceptible to modeling attacks, requiring the adoption of various design approaches to increase their resiliency. Many research efforts propose design approaches that offer better security against modeling attacks. This work investigates state-of-the-art modeling attacks performed on well-known Arbiter-based PUF architectures highlighting the best-fit modeling algorithm for different design approaches. Furthermore, the area efficiency of studied PUF designs is examined, and the optimal PUF design approaches for various area constraints are suggested. Such an assessment is required to evaluate PUF security accurately and guide the PUF community toward better practices. The findings revealed that some machine-learning algorithms performed better on a particular design. Additionally, when considering area overhead, we found that some PUF designs offer less security per area unit than their simpler counterparts. Accordingly, certain design elements are more efficient and add more security.","PeriodicalId":177320,"journal":{"name":"2023 IEEE International Symposium on Circuits and Systems (ISCAS)","volume":"73 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-05-21","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130123557","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
{"title":"An Efficient Frequency Domain Vision Pipeline From RAW Images to Backend Tasks","authors":"Hao Li, Weiti Zhou, Xiangyu Zhang, Xin Lou","doi":"10.1109/ISCAS46773.2023.10182018","DOIUrl":"https://doi.org/10.1109/ISCAS46773.2023.10182018","url":null,"abstract":"Though high resolution benefits computer vision performance, they are not commonly used in convolutional neural network (CNN)-based vision algorithms due to the limitation of memory and computation resource. Learning in the frequency domain makes high resolution images directly acceptable by CNNs, but the computation, time and energy overhead for pre-processing, including image signal processing (ISP) and domain transformation, can be large. This paper explores different image processing and domain transformation operations and proposes an efficient end-to-end frequency domain learning pipeline from RAW images to vision tasks. In particular, we simplify the pre-processing part by skipping the entire ISP pipeline and replacing the Discrete Cosine Transform (DCT) with a multiplication-free approximated one. Experimental results show that the final vision performance of the proposed pipeline is very close to that of the conventional pipeline, while significant amount of redundant operations can be saved.","PeriodicalId":177320,"journal":{"name":"2023 IEEE International Symposium on Circuits and Systems (ISCAS)","volume":"33 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-05-21","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130232644","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
{"title":"Concealable Physically Unclonable Functions and Key Generation Using a Geiger Mode Imager","authors":"Md. Sakibur Rahman Sajal, M. Dandin","doi":"10.1109/ISCAS46773.2023.10182123","DOIUrl":"https://doi.org/10.1109/ISCAS46773.2023.10182123","url":null,"abstract":"We report a novel hardware method for generating authentication keys based on a physically unclonable function (PUF) of a perimeter-gated single photon avalanche diode (pg-SPAD) imager. We tested three $64times 64$ pg-SPAD imagers over a temperature range extending from 27°C to 75°C and demonstrated that authentication keys can be generated with quantifiable difference and that they are resilient to temperature change. We used the imager's spatial dark count variation as a PUF, i.e., as a means to generate unique hardware fingerprints on which the keys are based. Without applying complex key generation algorithms or temperature compensation techniques, we obtained approximately 0.1 in average normalized Hamming distance (nHD) between intra-chip keys generated from the same challenge and approximately 0.5 in average nHD between intra-chip keys generated from different challenges. Inter-chip keys generated with the same challenge also showed sufficient differentiation, i.e., a nHD of approximately 0.5. Additionally, we demonstrate that perimeter gating offers an additional security feature as it can either alter or obfuscate the imager's PUF.","PeriodicalId":177320,"journal":{"name":"2023 IEEE International Symposium on Circuits and Systems (ISCAS)","volume":"49 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-05-21","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"134152943","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
J. Zeng, Tsung-Yi Wu, Don-Gey Liu, Ching-Hwa Cheng
{"title":"Live Demonstration: A Low-Power Dual-Core Motion Estimation Chip Design and Validation for a Wireless Panoramic Endoscopy","authors":"J. Zeng, Tsung-Yi Wu, Don-Gey Liu, Ching-Hwa Cheng","doi":"10.1109/ISCAS46773.2023.10181322","DOIUrl":"https://doi.org/10.1109/ISCAS46773.2023.10181322","url":null,"abstract":"A low-power motion estimation chip is designed for a wireless panoramic endoscope system. This chip consists of two motion estimation cores and is implemented by a dual-Vdd low-power technique. The proposed technique is efficient in decreasing power consumption without reducing the operation frequency of the chip. From the full-function chip measurements, this dual-Vdd chip can reduce power consumption by 20%~40% than the operation in single-Vdd for different clock frequencies.","PeriodicalId":177320,"journal":{"name":"2023 IEEE International Symposium on Circuits and Systems (ISCAS)","volume":"200 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-05-21","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"133884900","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Yan-Cheng Guo, Wei-Tien Lin, T. Hou, Tian-Sheuan Chang
{"title":"FPCIM: A Fully-Parallel Robust ReRAM CIM Processor for Edge AI Devices","authors":"Yan-Cheng Guo, Wei-Tien Lin, T. Hou, Tian-Sheuan Chang","doi":"10.1109/ISCAS46773.2023.10181402","DOIUrl":"https://doi.org/10.1109/ISCAS46773.2023.10181402","url":null,"abstract":"Computing-in-memory (CIM) is popular for deep learning due to its high energy efficiency owing to massive parallelism and low data movement. However, current ReRAM based CIM designs only use partial parallelism since fully parallel CIM could suffer lower model accuracy due to severe nonideal effects. This paper proposes a robust fully-parallel ReRAM-based CIM processor for deep learning. The proposed design exploits the fully-parallel computation of a $1024mathrm{x}1024$ array to achieve 110.59 TOPS and reduces nonideal effects with in-ReRAM computing (IRC) training and hybrid digital/IRC design to minimize the accuracy loss with only 1.55%. This design is programmable with a compact CIM-oriented instruction set to support various 2-D convolution neural networks (NN) as well as hybrid digital/IRC designs. The final implementation achieves a 2740.41 TOPS/W energy efficiency at 125MHz with TSMC 40nm technology, which is superior to previous designs.","PeriodicalId":177320,"journal":{"name":"2023 IEEE International Symposium on Circuits and Systems (ISCAS)","volume":"11 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-05-21","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"133912819","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Yaswanth K. Cherivirala, Mehdi Saligane, D. Wentzloff
{"title":"An Open Source Compatible Framework to Fully Autonomous Digital LDO Generation","authors":"Yaswanth K. Cherivirala, Mehdi Saligane, D. Wentzloff","doi":"10.1109/ISCAS46773.2023.10181884","DOIUrl":"https://doi.org/10.1109/ISCAS46773.2023.10181884","url":null,"abstract":"This work presents an open-source methodology to automate the design and layout of a low dropout (LDO) regulator from high-level performance specifications. LDO designs with this methodology have been demonstrated in commercial 65nm, 12nm, 130nm processes and the open-source 130nm Skywater PDK. The tool currently supports LDO designs with 50mV/100mV dropout for an input voltage range of 0.6V-1.3V (130nm and 65nm), 0.6V-0.9V (12nm), 1.8V-3.3V (Skywater 130nm) and a maximum load current ranging from 0.5mA-25mA (130nm and 65nm), 1mA-20mA (12nm), 0.5mA-50mA (Skywater 130nm). Cell-based design approach is adopted using an auxiliary cell library to enable mixed-signal design synthesis. A port to a new technology only requires a one-time manual layout for auxiliary library generation. The design automation includes a technology-agnostic modeling step and generates the LDO layout automatically. A bi-directional shift register based DLDO with a 1-bit comparator and a stochastic flash ADC (achieving 15x faster settling time) for error detection has been generated using the tool and validated using silicon measurements from 65nm process. LDO designs with different switch types and load configurations have been fabricated in open-source Skywater 130nm.","PeriodicalId":177320,"journal":{"name":"2023 IEEE International Symposium on Circuits and Systems (ISCAS)","volume":"43 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-05-21","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"131590176","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}