2021 22nd International Symposium on Quality Electronic Design (ISQED)最新文献_第3页

Conditional Classification: A Solution for Computational Energy Reduction 条件分类:一种减少计算能量的方法

2021 22nd International Symposium on Quality Electronic Design (ISQED) Pub Date : 2021-04-07 DOI: 10.1109/ISQED51717.2021.9424280

Ali Mirzaeian, Sai Manoj Pudukotai Dinakarrao, Ashka Vakil, H. Homayoun, Avesta Sasan

引用次数: 1

Automatic Generation of Translators for Packet-Based and Emerging Protocols 基于分组和新兴协议的自动生成翻译器

2021 22nd International Symposium on Quality Electronic Design (ISQED) Pub Date : 2021-04-07 DOI: 10.1109/ISQED51717.2021.9424338

Brian Crafton, A. Raychowdhury, S. Lim

引用次数: 0

Novel Memristor-based Nonvolatile D Latch and Flip-flop Designs 基于忆阻器的新型非易失D锁存器和触发器设计

2021 22nd International Symposium on Quality Electronic Design (ISQED) Pub Date : 2021-04-07 DOI: 10.1109/ISQED51717.2021.9424269

Zhenxing Chang, Aijiao Cui, Ziming Wang, G. Qu

{"title":"Novel Memristor-based Nonvolatile D Latch and Flip-flop Designs","authors":"Zhenxing Chang, Aijiao Cui, Ziming Wang, G. Qu","doi":"10.1109/ISQED51717.2021.9424269","DOIUrl":"https://doi.org/10.1109/ISQED51717.2021.9424269","url":null,"abstract":"Sequential devices are the fundamental building blocks for almost all digital electronic systems with memory. Due to the importance of instant data recovery after unexpected data loss such as unplanned power down, sequential devices need to have the nonvolatile property, which motivates the recent research and practice in integrating the nonvolatile memristor into CMOS devices. In this paper, we study how to apply this approach to improve the quality of nonvolatile D latch. Unlike the structure of conventional design, the proposed D latch consists of only one memristor, several transmission gates, and CMOS inverters. Our design overcomes the negative effect due to the threshold loss of the transistors. As simulation shows, compared with the current designs, our proposed memristor-based D latch can support the memristor to switch between different resistance states 2.3X-3.6X faster, and thus achieving a clock of higher frequency. In addition, our design allows the threshold value of the memristor to be selected from a much wider range. As an application, we use the proposed memristor-based D latch to implement a nonvolatile master-slave D flip-flop, which has smaller delay than all the state-of the-art designs and smaller area than all but one of them. Our designs improve the quality of memristor-based D latch and D flip-flop in terms of latency, area, and flexibility of threshold voltage selection, making them a promising option for data backup in real life systems.","PeriodicalId":123018,"journal":{"name":"2021 22nd International Symposium on Quality Electronic Design (ISQED)","volume":"117 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-04-07","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"132941094","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}

引用次数: 1

Cell-Aware Diagnosis of Customer Returns Using Bayesian Inference 基于贝叶斯推理的细胞感知顾客退货诊断

2021 22nd International Symposium on Quality Electronic Design (ISQED) Pub Date : 2021-04-07 DOI: 10.1109/ISQED51717.2021.9424337

S. Mhamdi, P. Girard, A. Virazel, A. Bosio, A. Ladhar

引用次数: 0

Flash ADC Utilizing Offset Voltage Variation With Order Statistics Based Comparator Selection 利用偏置电压变化和阶数统计选择比较器的Flash ADC

2021 22nd International Symposium on Quality Electronic Design (ISQED) Pub Date : 2021-04-07 DOI: 10.1109/ISQED51717.2021.9424288

T. Kitamura, Mahfuzul Islam, T. Hisakado, O. Wada

引用次数: 1

An End-to-end Multi-task Object Detection using Embedded GPU in Autonomous Driving 基于嵌入式GPU的自动驾驶端到端多任务目标检测

2021 22nd International Symposium on Quality Electronic Design (ISQED) Pub Date : 2021-04-07 DOI: 10.1109/ISQED51717.2021.9424308

Shangli Zhou, Mimi Xie, Yufang Jin, Fei Miao, Caiwen Ding

{"title":"An End-to-end Multi-task Object Detection using Embedded GPU in Autonomous Driving","authors":"Shangli Zhou, Mimi Xie, Yufang Jin, Fei Miao, Caiwen Ding","doi":"10.1109/ISQED51717.2021.9424308","DOIUrl":"https://doi.org/10.1109/ISQED51717.2021.9424308","url":null,"abstract":"Autonomous driving has gained popularity due to its high reliability compared to human drivers. Autonomous vehicles combine variety of sensors to perceive their surroundings, and use deep learning (DL) to extract complicated information from the sensing data. However, there are several challenges: Many DL models have explosive model sizes, and therefore not only time consuming but also power consuming when implementing on embedded systems on vehicles, further degrading the battery life-cycle. The current on-board AI treats lane detection and car location separately. In this paper, we propose an end-to-end multi-task environment detection framework. We fuse the 3D point cloud object detection model and lane detection model, with model compression technique applied. As on-board sensors forward information to the multi-task network, it not only parallel two detection tasks to extract combination information, but also reduces entire running time of the DL model. Experiments show by adding the model compression technique, the running speed of multi-task model improves more than $2times$. Also, running time of lane detection model on Nvidia Jetson TX2 is almost $6times$ less comparing with running on CPU, which shows reasonableness of using embedded AI computing device on autonomous vehicle.","PeriodicalId":123018,"journal":{"name":"2021 22nd International Symposium on Quality Electronic Design (ISQED)","volume":"58 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-04-07","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"122997968","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}

引用次数: 13

Improving DNN Fault Tolerance using Weight Pruning and Differential Crossbar Mapping for ReRAM-based Edge AI 基于rram边缘人工智能的权值剪枝和差分横杆映射提高DNN容错性

2021 22nd International Symposium on Quality Electronic Design (ISQED) Pub Date : 2021-04-07 DOI: 10.1109/ISQED51717.2021.9424332

Geng Yuan, Zhiheng Liao, Xiaolong Ma, Yuxuan Cai, Zhenglun Kong, Xuan Shen, Jingyan Fu, Zhengang Li, Chengming Zhang, Hongwu Peng, Ning Liu, Ao Ren, Jinhui Wang, Yanzhi Wang

{"title":"Improving DNN Fault Tolerance using Weight Pruning and Differential Crossbar Mapping for ReRAM-based Edge AI","authors":"Geng Yuan, Zhiheng Liao, Xiaolong Ma, Yuxuan Cai, Zhenglun Kong, Xuan Shen, Jingyan Fu, Zhengang Li, Chengming Zhang, Hongwu Peng, Ning Liu, Ao Ren, Jinhui Wang, Yanzhi Wang","doi":"10.1109/ISQED51717.2021.9424332","DOIUrl":"https://doi.org/10.1109/ISQED51717.2021.9424332","url":null,"abstract":"Recent research demonstrated the promise of using resistive random access memory (ReRAM) as an emerging technology to perform inherently parallel analog domain in-situ matrix-vector multiplication—the intensive and key computation in deep neural networks (DNNs). However, hardware failure, such as stuck-at-fault defects, is one of the main concerns that impedes the ReRAM devices to be a feasible solution for real implementations. The existing solutions to address this issue usually require an optimization to be conducted for each individual device, which is impractical for mass-produced products (e.g., IoT devices). In this paper, we rethink the value of weight pruning in ReRAM-based DNN design from the perspective of model fault tolerance. And a differential mapping scheme is proposed to improve the fault tolerance under a high stuck-on fault rate. Our method can tolerate almost an order of magnitude higher failure rate than the traditional two-column method in representative DNN tasks. More importantly, our method does not require extra hardware cost compared to the traditional two-column mapping scheme. The improvement is universal and does not require the optimization process for each individual device.","PeriodicalId":123018,"journal":{"name":"2021 22nd International Symposium on Quality Electronic Design (ISQED)","volume":"10 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-04-07","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"123969120","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}

引用次数: 22

SolicitudeSavvy: An IoT-based Edge Intelligent Framework for Monitoring Anxiety in Real-time SolicitudeSavvy:一个基于物联网的边缘智能框架，用于实时监测焦虑

2021 22nd International Symposium on Quality Electronic Design (ISQED) Pub Date : 2021-04-07 DOI: 10.1109/ISQED51717.2021.9424302

P. Sundaravadivel, Parker Wilmoth, Ashton Fitzgerald

{"title":"SolicitudeSavvy: An IoT-based Edge Intelligent Framework for Monitoring Anxiety in Real-time","authors":"P. Sundaravadivel, Parker Wilmoth, Ashton Fitzgerald","doi":"10.1109/ISQED51717.2021.9424302","DOIUrl":"https://doi.org/10.1109/ISQED51717.2021.9424302","url":null,"abstract":"Anxiety disorders affect more than 18 percent of the population and is the most common mental illnesses in the US. There is a great demand to address this emerging epidemic with tools to differentiate and diagnose such disorders, and to create awareness especially in places like NorthEast Texas which is home to 1.5 million people with 58 percent of them living in rural areas. The goal of the proposed device is to diagnose as many anxiety disorders as possible, in real-time using the diagnosing wearable framework, SolicitudeSavvy, which uses technology such as the Internet of Things (IoT), a network of interconnected devices, to accomplish such a task. The proposed IoT-based device has two components: a custom-built wearable necklace that contains sensors to collect data about the user as they go about their day and a low-cost portable system that monitors Electrooculography (EoG) signal using a camera. The partial necklace attaches to the shirt and opens halfway around the wearer's neck and the EoG can be attached to any eyewear. The device monitors the user throughout the day, and even as they go to bed at night. This information is accumulated in the IoT cloud and analyzed to see exactly what type of disorder(s) the patient may suffer from. The authorized personnel i.e. doctor or therapist, can use this pattern to find a treatment that best suits them and is most likely to resolve their affliction.","PeriodicalId":123018,"journal":{"name":"2021 22nd International Symposium on Quality Electronic Design (ISQED)","volume":"3 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-04-07","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"128285007","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}

引用次数: 2

SeNonDiv: Securing Non-Volatile Memory using Hybrid Memory and Critical Data Diversion SeNonDiv:使用混合存储器和关键数据转移保护非易失性存储器

2021 22nd International Symposium on Quality Electronic Design (ISQED) Pub Date : 2021-04-07 DOI: 10.1109/ISQED51717.2021.9424292

Arijit Nath, Manik B. Bhosle, H. Kapoor

引用次数: 0

Design Space Extrapolation for Power Delivery Networks using a Transposed Convolutional Net 基于转置卷积网络的输电网络空间外推设计

2021 22nd International Symposium on Quality Electronic Design (ISQED) Pub Date : 2021-04-07 DOI: 10.1109/ISQED51717.2021.9424309

O. W. Bhatti, M. Swaminathan

引用次数: 1