{"title":"An Imu-Based Wearable Ring For On-Surface Handwriting Recognition","authors":"Zhe-Ting Liu, Davy P. Y. Wong, Pai H. Chou","doi":"10.1109/VLSI-DAT49148.2020.9196479","DOIUrl":"https://doi.org/10.1109/VLSI-DAT49148.2020.9196479","url":null,"abstract":"We propose a finger-worn, on-surface fingerwriting recognition system based on an inertial sensor. The acceleration and the angular velocity data from the finger are sent by Bluetooth (BLE) to a host computer for conversion into words. The motion data are segmented by a long short-term memory (LSTM) model before recognition by a Convolutional Neural Network (CNN) or an LSTM model. Experiment results show the proposed system achieves 1.05% CER and 7.28% WER, making it a viable system as a text input interface.","PeriodicalId":235460,"journal":{"name":"2020 International Symposium on VLSI Design, Automation and Test (VLSI-DAT)","volume":"68 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-08-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"124220340","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}
Weida Zhu, Xinghai Zhang, Genggeng Liu, Wenzhong Guo, Ting-Chi Wang
{"title":"MiniDeviation: An Efficient Multi-Stage Bus-Aware Global Router","authors":"Weida Zhu, Xinghai Zhang, Genggeng Liu, Wenzhong Guo, Ting-Chi Wang","doi":"10.1109/VLSI-DAT49148.2020.9196219","DOIUrl":"https://doi.org/10.1109/VLSI-DAT49148.2020.9196219","url":null,"abstract":"As the number of signal nets increases significantly, global routing of buses becomes an increasingly important and difficult problem. In this paper, to match the timing of buses, we propose an efficient multi-stage bus-aware global routing algorithm called MiniDeviation that is based on several techniques: 1) a deviation-driven segment shifting, 2) a multi-stage double maze routing strategy, and 3) a post-routing scheme. Compared with the existing algorithms, the experimental results show that the proposed global router achieves the best results for both total wirelength deviation and total overflow.","PeriodicalId":235460,"journal":{"name":"2020 International Symposium on VLSI Design, Automation and Test (VLSI-DAT)","volume":"29 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-08-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"121064496","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}
R. Panek, Jakub Lojda, Jakub Podivinsky, Z. Kotásek
{"title":"Reliability Analysis of Reconfiguration Controller for FPGA–Based Fault Tolerant Systems: Case Study","authors":"R. Panek, Jakub Lojda, Jakub Podivinsky, Z. Kotásek","doi":"10.1109/VLSI-DAT49148.2020.9196269","DOIUrl":"https://doi.org/10.1109/VLSI-DAT49148.2020.9196269","url":null,"abstract":"This paper deals with a reliability analysis of a reconfiguration controller which can be a component of a faulttolerant control system. This controller is designed for an FPGA to be capable of using partial dynamic reconfiguration of the FPGA to mitigate potential faults in the FPGA’s configuration memory. These faults, which are called SEUs, can be induced by radiation effects. Therefore, fault tolerance measurement or estimation is very important for designing circuits for critical environments. Thus, the reliability of the reconfiguration controller itself is significant; therefore the Fault Tolerance ESTimation (FT-EST) framework is used for reliability evaluation, which is procured by the discovery of a number of critical configuration bits. Two approaches are used and compared: evaluations of used LUT only, and evaluations of all configuration bits. We ascertained a 20x reduction in time consumption at the expense of a proportional decrease in the amount of critical configuration bits discovered. The obtained results are nearly equivalent.","PeriodicalId":235460,"journal":{"name":"2020 International Symposium on VLSI Design, Automation and Test (VLSI-DAT)","volume":"82 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-08-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"122933802","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}
Zhen-Cheng Zhang, Chun-Yuan Chiu, Hsiang-Cheng Yuan, Tsung-Hsien Lin
{"title":"A 0.5-V, 1.79-μW, 250-kbps Wake-up Receiver for IoT application in 90-nm CMOS","authors":"Zhen-Cheng Zhang, Chun-Yuan Chiu, Hsiang-Cheng Yuan, Tsung-Hsien Lin","doi":"10.1109/VLSI-DAT49148.2020.9196261","DOIUrl":"https://doi.org/10.1109/VLSI-DAT49148.2020.9196261","url":null,"abstract":"This paper presents the design of a low-power wake-up receiver (WuRX). The proposed WuRX composed of an active envelope detector with high input impedance to support high passive gain, a self-biased high-gain IF-amplifier, a dynamic comparator, and a proposed level-tracking calibration circuit that mitigates circuit drift. This OOK-modulated WuRX is implemented in a 90-nm CMOS process and operates at the 400-MHz MICS band. Operated from a 0.5-V supply, this WuRX consumes 1.79-W. It supports 250-kbps data rate and achieves -40-dBm sensitivity.","PeriodicalId":235460,"journal":{"name":"2020 International Symposium on VLSI Design, Automation and Test (VLSI-DAT)","volume":"2 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-08-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"121468648","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 24 Mbit/s Red LED-based Visible Light Communication System Employing DCO-OFDM Modulation","authors":"Yu-Jung Wang, Siou-Lin You, Zhen-Hao Zhu, Wei-Ting Lin, Cheng-You Ho, Chi-Lun Hsu, Chun-Hsing Lee, Hsi-Pin Ma","doi":"10.1109/VLSI-DAT49148.2020.9196282","DOIUrl":"https://doi.org/10.1109/VLSI-DAT49148.2020.9196282","url":null,"abstract":"In this paper, we present a 24 Mbit/s visible light communication (VLC) system based on red light emitting diode (LED). For VLC systems, intensity modulation with direct detection (IM/DD) is widely used, which means that the transmitted signal must be nonnegative and real-valued. In this system, we implemented the DCbiased optical orthogonal frequency division multiplexing (DCOOFDM) architecture and solved the synchronization problem in OFDM systems. In addition, the least square (LS) algorithm is used to estimate channel response. We add partial transmit sequence (PTS) and clipping method to reduce the problem of high peak-to-average power ratio (PAPR) in OFDM system. Bit error rates (BER) is zero under 15 cm free space transmission.","PeriodicalId":235460,"journal":{"name":"2020 International Symposium on VLSI Design, Automation and Test (VLSI-DAT)","volume":"30 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-08-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126038817","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}
K. Sasagawa, M. Haruta, Yasumi Ohta, H. Takehara, J. Ohta
{"title":"Miniaturized CMOS imaging device for implantable applications","authors":"K. Sasagawa, M. Haruta, Yasumi Ohta, H. Takehara, J. Ohta","doi":"10.1109/VLSI-DAT49148.2020.9196250","DOIUrl":"https://doi.org/10.1109/VLSI-DAT49148.2020.9196250","url":null,"abstract":"Optical observation of brain activities is very important to elucidate brain functions. The imaging of numerous kinds of cell activities can be observed by microscopes and image sensors with a help of fluorescent or bioluminescent labels. Recently, miniaturized microscopes that can be mounted on the mouse head have been developed. These devices enable observation of mouse brain under freely moving conditions.","PeriodicalId":235460,"journal":{"name":"2020 International Symposium on VLSI Design, Automation and Test (VLSI-DAT)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-08-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"132687648","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":"Deep Learning Creativity in EDA","authors":"C. Lee","doi":"10.1109/VLSI-DAT49148.2020.9196288","DOIUrl":"https://doi.org/10.1109/VLSI-DAT49148.2020.9196288","url":null,"abstract":"Computing power brings new technologies into human life. NVIDIA devoted to accelerating parallel computing through CPU-GPU cooperating architecture since we invented CUDA in 2007. In the last decade, one of the most important technologies, deep learning, became feasible and realistic because GPU accelerates the optimizing process of neural network over 60x, which means that the model training time shortens from weeks to hours. DL not only performed superior to human in some computer vision tasks like ImageNet but also made significant progress of many fields like medical, autonomous, manufacturing, finance, electronic design automation (EDA) etc.In this paper, we introduced two deep learning innovations in EDA field including (1) Graph Convolutional Network in Testability Analysis and (2) DREAMPlace. In (1), graph convolutional network can predict observation point candidates in a netlist more efficiently compared to commercial tools. In (2), DREAMPlace significantly accelerates the VLSI placement process by using deep learning framework of GPU for optimizing process.","PeriodicalId":235460,"journal":{"name":"2020 International Symposium on VLSI Design, Automation and Test (VLSI-DAT)","volume":"22 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-08-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"115466086","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}
Shu-Ming Liu, Luba Tang, N. Huang, Der-Yu Tsai, Ming Yang, Kai-Chiang Wu
{"title":"Fault-Tolerance Mechanism Analysis on NVDLA-Based Design Using Open Neural Network Compiler and Quantization Calibrator","authors":"Shu-Ming Liu, Luba Tang, N. Huang, Der-Yu Tsai, Ming Yang, Kai-Chiang Wu","doi":"10.1109/VLSI-DAT49148.2020.9196335","DOIUrl":"https://doi.org/10.1109/VLSI-DAT49148.2020.9196335","url":null,"abstract":"The NVIDIA Deep Learning Accelerator (NVDLA) provides free intellectual property licensing to IC chip vendors and researchers to build a chip that uses deep neural networks for inference applications. The Open Neural Network Compiler (ONNC) provides an extensible compiler, a quantization calibrator and optimization supports for running DNN models on NVDLA-based SoCs. Even with open-sourced NVDLA and ONNC, conducting the development of an AI chip still brings up many productivity issues in the mass production stage, such as SRAM MBIST (Memory Built-In Self Test) fail, scan-chain fail etc. When applying Fault-Tolerance Mechanism in error-tolerant applications such as image classification by using the AI CNN model, this paper presents a light-weight Fault-Tolerance Mechanism to effectively enhance the robustness of NVDLA-based edge AI chip when encountering internal SRAM stuck fault. Our non-accurate MAC calculation for the whole convolution computation leads to a very promising quality of results compared to the case when an exactly accurate convolution operation is used. The Fault-Tolerance Mechanism analysis and design described in this paper can also apply to the similar fixed-point deep learning accelerator design, and opens new opportunities for research as well as product development.","PeriodicalId":235460,"journal":{"name":"2020 International Symposium on VLSI Design, Automation and Test (VLSI-DAT)","volume":"26 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-08-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"123778708","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":"Low-Power 3D-PCB Stacking System Design and Validation by Automatic Voltage-Current Scalable Technique","authors":"Ching-Hwa Cheng, Jiun-In Guo","doi":"10.1109/VLSI-DAT49148.2020.9196244","DOIUrl":"https://doi.org/10.1109/VLSI-DAT49148.2020.9196244","url":null,"abstract":"The proposed design is integrating multiple video and power-regulate chips integrated with a low-power 3D-PCB Stacking system. This performance-power optimized 3D-PCB Stacking SoC system is corroborated by the dual multi-mode video decoder (MMVD) and five voltage-current adjustors (VCAs) chips. Low-power dual-Vdd design techniques are utilized in MMVD, without using level converters. The VCA is used to supply manageable power-current to MMVD. The automated voltage-current adjusted technique does not increase the additional silicon cost without using voltage converters. The low-power contribution is to utilize current-adjusted technique for an automation voltage-adjustor. A built-in voltage measurement provides voltage-level can be safely regulated.The system achieves a 32 $sim$ 68% power reduction for two video decoders by using the VCAs. The system scalable function is implemented by a MorPack 3D-PCB stacking design. The proposed technique is success validated reduce system power consumption and without performance degradation.","PeriodicalId":235460,"journal":{"name":"2020 International Symposium on VLSI Design, Automation and Test (VLSI-DAT)","volume":"37 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-08-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"127121821","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":"Cost-Effective Reliable Edge Computing Hardware Design Based on Module Simplification and Duplication: A Case Study on Vehicle Detection Based on Support Vector Machine","authors":"Tong-Yu Hsieh, Hsin-Yung Shen, Chia-Teng Hsu","doi":"10.1109/VLSI-DAT49148.2020.9196386","DOIUrl":"https://doi.org/10.1109/VLSI-DAT49148.2020.9196386","url":null,"abstract":"Autonomous vehicles and advanced driver assistance systems (ADAS) have recently become quite popular research topics. While autonomous vehicles may not be totally ready now, ADAS has been applied to many vehicles. The implementation of ADAS partly relies on detection of vehicles via edge computing. However, the edge computing hardware may age and incur functional errors. Soft errors may also be caused due to cosmic charged particles. These errors may invalidate the vehicle detection result, thereby incurring serious safety threats. In this paper we investigate on designing a cost-effective reliable edge computing circuit. A case study on vehicle detection is considered where a support vector machine is implemented for illustration purpose. We find that in edge computing hardware, several multiplier-accumulator (MAC) units can be removed without sacrificing detection accuracy. A simple yet effective procedure is also proposed to identify such MAC units. The saved hardware can then be utilized to protect the remaining hardware, reducing the required hardware cost. Numeric fault simulations are first performed to identify which circuit lines need to be protected such that there is no loss on the vehicle detection accuracy due to faults. Then, for these lines, proper protection methods are investigated based on evaluation of their required hardware cost and fault-induced accuracy loss. Accordingly a hybrid protection scheme is developed, which achieves up to 153% hardware cost reduction when compared to the typical TMR-based protection method.","PeriodicalId":235460,"journal":{"name":"2020 International Symposium on VLSI Design, Automation and Test (VLSI-DAT)","volume":"38 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-08-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"127221741","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}