Dongqin Zhou, Keni Qiu, Yuanchao Xu, Xin Shi, Yongpan Liu
{"title":"A Dual-Threshold Scheme Along with Security Reinforcement for Energy Efficient Nonvolatile Processors","authors":"Dongqin Zhou, Keni Qiu, Yuanchao Xu, Xin Shi, Yongpan Liu","doi":"10.1109/ISVLSI.2018.00023","DOIUrl":"https://doi.org/10.1109/ISVLSI.2018.00023","url":null,"abstract":"With the increasing scale and decreasing size of the Internet of Things (IoTs) devices, energy harvesting systems have been proposed to power the systems instead of batteries. Addressing the problem that harvested energy is unstable, nonvolatile processors (NVPs) have been proposed to hold intermediate data and avoid frequent program restarting from the beginning. However, NVPs often suffer frequent backup and recovery operations, wasting a lot of energy and system resources. To further improve the performance of NVPs, this paper proposes a dual-threshold method to maximize execution progress by enabling a system to hibernate to wait for power resumption instead of backing up data directly upon power interruptions. In particular, the appropriate retention and backup thresholds are discussed in details in order to achieve the goal of minimizing power failures and maximizing computation progress. In the meantime, the possible attacks to NVPs with dual-threshold and solutions combating these threats are discussed to guarantee NVP's security. The evaluation results show an average of up to 82.3% reduction on power failures and 1.5x speedup on forward progress by the proposed dual-threshold method compared to the conventional single threshold scheme.","PeriodicalId":114330,"journal":{"name":"2018 IEEE Computer Society Annual Symposium on VLSI (ISVLSI)","volume":"2 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-07-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"132703565","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}
Yang Nan, Chenchang Zhan, Guanhua Wang, Linjun He, Han Li
{"title":"Replica-Based Low Drop-Out Voltage Regulator with Assistant Power Transistors for Digital VLSI Systems","authors":"Yang Nan, Chenchang Zhan, Guanhua Wang, Linjun He, Han Li","doi":"10.1109/ISVLSI.2018.00012","DOIUrl":"https://doi.org/10.1109/ISVLSI.2018.00012","url":null,"abstract":"An advanced replica-based low drop-out (LDO) voltage regulator with assistant power transistors and bulk modulation digital VLSI systems is proposed in this paper. It utilizes seven current comparators with different aspect sizes to control seven assistant power transistors to compensate for the load current. As a result, the load regulation of the replica LDO is significantly improved, while the wide-load-range-stability which is critical for digital systems is not compromised. The proposed LDO is designed in a standard 0.18-mm CMOS process. Extensive simulation results show that, with a power supply of 1.2 V and output voltage of 1.0 V, the proposed LDO has a dropout voltage of 200mV when delivering 1~100mA to the load. The load regulation is 0.148mV/mA, and the supported load capacitance range is from 0 to 100nF.","PeriodicalId":114330,"journal":{"name":"2018 IEEE Computer Society Annual Symposium on VLSI (ISVLSI)","volume":"275 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-07-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"133197974","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}
Hao Geng, Haoyu Yang, Bei Yu, Xingquan Li, Xuan Zeng
{"title":"Sparse VLSI Layout Feature Extraction: A Dictionary Learning Approach","authors":"Hao Geng, Haoyu Yang, Bei Yu, Xingquan Li, Xuan Zeng","doi":"10.1109/ISVLSI.2018.00094","DOIUrl":"https://doi.org/10.1109/ISVLSI.2018.00094","url":null,"abstract":"Recently, in VLSI design for manufacturability (DFM), capturing and representing the intrinsic characteristics of a layout is of great importance. Especially, there has been revival of interest in applying machine learning techniques into DFM field. Feature extraction of layout patterns is imperative before feeding into learning models so that feature representation directly affects performance of machine learning model. In this paper, a literature review of recent progress on VLSI layout feature extraction is firstly conducted. Then, for the first time, we propose a dictionary learning approach wrapped in an online learning model in applications of VLSI layout such as sub-resolution assist feature (SRAF) generation and hotspot detection. With mapping original features into a sparse and low-dimension space, dictionary learning model is benefit to calibrate a machine learning model. The experimental results show that our method not only improves the accuracy of hotspot detection but also boosts F1 score in machine learning model-based SRAF generation with less time overhead.","PeriodicalId":114330,"journal":{"name":"2018 IEEE Computer Society Annual Symposium on VLSI (ISVLSI)","volume":"50 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-07-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"132891738","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. Choi, S. Srinivasa, Yasuki Tanabe, J. Sampson, N. Vijaykrishnan
{"title":"A Power-Efficient Hybrid Architecture Design for Image Recognition Using CNNs","authors":"J. Choi, S. Srinivasa, Yasuki Tanabe, J. Sampson, N. Vijaykrishnan","doi":"10.1109/ISVLSI.2018.00015","DOIUrl":"https://doi.org/10.1109/ISVLSI.2018.00015","url":null,"abstract":"Convolutional Neural Networks (CNNs) are proving to be highly effective in vision recognition systems. However, it is a challenge to use them in real-time embedded systems because of their requirements for computation-intensive operations and high memory bandwidth. This paper proposes a power-efficient CNN architecture that has a pipelined streaming accelerator coupled to 4,096 SIMD Processing Elements. We reduce memory bandwidth via hierarchical intermediate data buffering and batch processing on the chip. As a result, we achieve high power-efficiency: Our proposed design processes 2,175 regions/second when operating at 500MHz with a power budget less than 7.5 Watts.","PeriodicalId":114330,"journal":{"name":"2018 IEEE Computer Society Annual Symposium on VLSI (ISVLSI)","volume":"16 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-07-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"133845273","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}
Yu-Xiang Chiang, Cheng-Wei Tai, Shang-Rong Fang, Kai-Chun Peng, Yuan-Dar Chung, Jin-Kai Yang, Rung-Bin Lin
{"title":"Designing and Benchmarking of Double-Row Height Standard Cells","authors":"Yu-Xiang Chiang, Cheng-Wei Tai, Shang-Rong Fang, Kai-Chun Peng, Yuan-Dar Chung, Jin-Kai Yang, Rung-Bin Lin","doi":"10.1109/ISVLSI.2018.00022","DOIUrl":"https://doi.org/10.1109/ISVLSI.2018.00022","url":null,"abstract":"This article presents our experience of designing double-row height standard cell libraries and their use for chip designs. Seven cell libraries are designed based on the 15nm process technology stipulated in FreePDK15. A single-row height of 7.5 M2 tracks is used as a basis for designing double-row height cells. Two minimum-sized transistors, one having two fins and the other having four fins, are employed to design 1X drive-strength cells. Among the seven libraries, two libraries consist of only single-row height cells. The other five libraries each consist of partly single-row height cells and double-row height cells. Our experiments show that a double-row height library can achieve on average -2% to 21% area saving and -23% to 19% smaller power-delay-area product. Our results also show that using a large minimum-sized transistor for designing a double-row height library is not viable if extensive transistor folding is required.","PeriodicalId":114330,"journal":{"name":"2018 IEEE Computer Society Annual Symposium on VLSI (ISVLSI)","volume":"31 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-07-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"127977107","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":"Designing Scalable Hybrid Wireless NoC for GPGPUs","authors":"Hui Zhao, Xianwei Cheng, S. Mohanty, Juan Fang","doi":"10.1109/ISVLSI.2018.00132","DOIUrl":"https://doi.org/10.1109/ISVLSI.2018.00132","url":null,"abstract":"Data communication in GPU systems exhibits asymmetric patterns that create congestion hotspots. Due to their large number of cores and big die sizes, GPUs also demand highly scalable NoC designs. In this work, we propose hybrid NoC architectures that employ on-chip integrated antennas to build overlaid wireless networks on top of conventional metal/dielectric-based networks. We use low-power high-bandwidth wireless links as express channels to transmit long distance packets and use metal links to deliver local packets. The hybrid architecture can effectively alleviate congestion near traffic hotspots and improve the throughput and scalability of GPU NoCs. We propose solutions for design challenges in such hybrid NoC architectures, such as MAC protocol, router microarchitecture, load balancing and deadlock free routing. To efficiently utilize on-chip wireless bandwidth, we also propose a novel scheme that adaptively allocates bandwidth to wireless channels based on their usage needs. Our evaluation results show that for a GPU with 256 cores, the proposed hybrid architecture can improve performance by 2.4 times on average.","PeriodicalId":114330,"journal":{"name":"2018 IEEE Computer Society Annual Symposium on VLSI (ISVLSI)","volume":"41 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-07-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"122440247","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}
Donel Anto, Abhijeet D. Taralkar, Kumar Y. B. Nithin, M. H. Vasantha
{"title":"Performance Enhancement of Split Length Compensated Operational Amplifiers","authors":"Donel Anto, Abhijeet D. Taralkar, Kumar Y. B. Nithin, M. H. Vasantha","doi":"10.1109/ISVLSI.2018.00116","DOIUrl":"https://doi.org/10.1109/ISVLSI.2018.00116","url":null,"abstract":"In this work, a technique to improve the performance parameters of the split length compensated operational amplifiers is proposed. The proposed technique uses an assistant amplifier for performance enhancement of the system. The assistant amplifier is designed in such a way that it draws only a small amount of power (<2%). This work is simulated in 180 nm CMOS technology with 1.8 V supply using Cadence Virtuoso. It achieves 78 dB DC gain, 40.8 MHz unity gain bandwidth and a slew rate of 27.17 V/uS for a load capacitance of 15 pF.","PeriodicalId":114330,"journal":{"name":"2018 IEEE Computer Society Annual Symposium on VLSI (ISVLSI)","volume":"8 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-07-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"128400908","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. SiddharthR., R. Sunil, Nithin Y. B. Kumar, M. H. Vasantha, E. Bonizzoni
{"title":"An Asynchronous Analog to Digital Converter for Surveillance Camera Applications","authors":"K. SiddharthR., R. Sunil, Nithin Y. B. Kumar, M. H. Vasantha, E. Bonizzoni","doi":"10.1109/ISVLSI.2018.00039","DOIUrl":"https://doi.org/10.1109/ISVLSI.2018.00039","url":null,"abstract":"This paper proposes an asynchronous analog to digital converter (ADC) for surveillance camera applications. The proposed architecture is based on non-uniform sampling, whose sampling instants depend on the amplitude of the input voltage. The proposed design has the power performance advantage for an input voltage close to the upper reference voltage. Thus, the proposed architecture is suitable for the applications in which the input signal rarely assumes voltage values closer to the lower reference voltage. The design is simulated, at the transistor level, in a 180-nm CMOS technology. The results show that about 96.7% of the power can be saved in the best case (input voltage in the vicinity of upper reference voltage) when compared to a conventional flash ADC.","PeriodicalId":114330,"journal":{"name":"2018 IEEE Computer Society Annual Symposium on VLSI (ISVLSI)","volume":"45 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-07-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125476922","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}
G. Harsha, Mitali Sinha, Sidhartha Sankar Rout, Sujay Deb
{"title":"Enabling Reliable High Throughput On-chip Wireless Communication for Many Core Architectures","authors":"G. Harsha, Mitali Sinha, Sidhartha Sankar Rout, Sujay Deb","doi":"10.1109/ISVLSI.2018.00113","DOIUrl":"https://doi.org/10.1109/ISVLSI.2018.00113","url":null,"abstract":"Wireless Networks-on-Chip (WNoCs) have been shown to overcome the scaling challenges of wired NoCs by augmenting them with low latency, low energy, long range wireless links. However, existing wireless implementations face challenges in terms of reliability while providing high communication performance. Single channel communication, the pre-dominant way of implementing WNoCs, are susceptible to channel effects like dispersion, fading, etc. and also provide limited bandwidth. Multi-channel communication, though provides high throughput, are prone to inter-channel and inter-symbol interference. In order to handle both performance and reliability challenges, we propose wireless network design using Orthogonal Frequency Division Multiplexing (OFDM) modulation. The proposed design enables reliable and channel resilient wireless communication, while providing high throughput, concurrent transmissions in WNoC. OFDM, by dividing wide band channel into several smaller sub-channels, overcomes channel dispersion and ISI effects. In the proposed design, OFDM sub-channels are grouped into multiple contiguous bands and assigned to each transceiver in WNoC. By allowing each transceiver to transmit only over assigned group, we enable simultaneous, high bandwidth communications. Evaluations show that proposed design achieves BER of the order 10^-12. Using the concurrent wireless link design, the runtime is improved by 29% and network energy is reduced by 68% as compared to baseline mesh topology.","PeriodicalId":114330,"journal":{"name":"2018 IEEE Computer Society Annual Symposium on VLSI (ISVLSI)","volume":"2014 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-07-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"128015738","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":"Guiding Template-Induced Design Challenges in DSA-MP Lithography","authors":"Shao-Yun Fang, Kuo-Hao Wu","doi":"10.1109/ISVLSI.2018.00097","DOIUrl":"https://doi.org/10.1109/ISVLSI.2018.00097","url":null,"abstract":"Directed self-assembly (DSA) has become one of the most promising next generation lithography technologies especially for contact/via layer fabrication. Guiding templates are required to generate contact/via holes at desired positions, while there is only a limited number of feasible guiding templates and thus feasible via arrangements. On the other hand, guiding templates need to be first generated with conventional optical lithography, whose limited resolution causes the need of adopting multiple patterning (MP) technologies for dense template generation. This paper demonstrates the design challenges resulted from simultaneous contact/via assignment and layout decomposition of guiding templates, and state-of-the-art works are introduced to show the recent progress on DSA-MP-related optimization problems.","PeriodicalId":114330,"journal":{"name":"2018 IEEE Computer Society Annual Symposium on VLSI (ISVLSI)","volume":"6 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-07-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"133396382","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}