2022 IEEE Nordic Circuits and Systems Conference (NorCAS)最新文献

筛选
英文 中文
RF PA Predistortion using Non-Linear RF-DACs 使用非线性RF- dac的RF PA预失真
2022 IEEE Nordic Circuits and Systems Conference (NorCAS) Pub Date : 2022-10-25 DOI: 10.1109/NorCAS57515.2022.9934679
Victor Åberg, Hang Zhou, C. Fager, L. Svensson
{"title":"RF PA Predistortion using Non-Linear RF-DACs","authors":"Victor Åberg, Hang Zhou, C. Fager, L. Svensson","doi":"10.1109/NorCAS57515.2022.9934679","DOIUrl":"https://doi.org/10.1109/NorCAS57515.2022.9934679","url":null,"abstract":"Analog and/or digital predistortion may be used to linearize power amplifiers (PAs) at the cost of additional hardware. We present a novel scheme which uses segmented non-linear RF-DACs to linearize PAs at no additional hardware cost. An expanding segmented scaling chosen at design time may be adjusted using DAC bias, allowing linearization to be adapted. Simulations demonstrate the robustness and flexibility of the approach, achieving excellent overall linearity over a large range of DAC and PA bias conditions.","PeriodicalId":319833,"journal":{"name":"2022 IEEE Nordic Circuits and Systems Conference (NorCAS)","volume":"47 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-10-25","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"127213969","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
Python API for Kactus2 IP-XACT tool Kactus2 IP-XACT工具的Python API
2022 IEEE Nordic Circuits and Systems Conference (NorCAS) Pub Date : 2022-10-25 DOI: 10.1109/NorCAS57515.2022.9934343
E. Pekkarinen, Mikko Teuho, Timo Hämäläinen
{"title":"Python API for Kactus2 IP-XACT tool","authors":"E. Pekkarinen, Mikko Teuho, Timo Hämäläinen","doi":"10.1109/NorCAS57515.2022.9934343","DOIUrl":"https://doi.org/10.1109/NorCAS57515.2022.9934343","url":null,"abstract":"System-on-chip design is highly reliant on efficient tooling and commonly agreed standards. IP-XACT is the de-facto industry standard for exchanging design data, yet tool flows fail to fully leverage the information within. We present a Python application programming interface for Kactus2, an open-source IP-XACT design tool to improve the utilization of the standard in tool flows. The Python programming language is well understood, fast to develop and easy to interface with which motivated the language choice. We demonstrate the API applicability in a use case as a part of a recently taped-out System-on-Chip ASIC implementation.","PeriodicalId":319833,"journal":{"name":"2022 IEEE Nordic Circuits and Systems Conference (NorCAS)","volume":"45 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-10-25","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126574380","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: 0
DeepFlexiHLS: Deep Neural Network Flexible High-Level Synthesis Directive Generator DeepFlexiHLS:深度神经网络柔性高级合成指令生成器
2022 IEEE Nordic Circuits and Systems Conference (NorCAS) Pub Date : 2022-10-25 DOI: 10.1109/NorCAS57515.2022.9934617
M. Riazati, M. Daneshtalab, Mikael Sjödin, B. Lisper
{"title":"DeepFlexiHLS: Deep Neural Network Flexible High-Level Synthesis Directive Generator","authors":"M. Riazati, M. Daneshtalab, Mikael Sjödin, B. Lisper","doi":"10.1109/NorCAS57515.2022.9934617","DOIUrl":"https://doi.org/10.1109/NorCAS57515.2022.9934617","url":null,"abstract":"Deep Neural Networks (DNNs) are now widely adopted to solve various problems ranging from speech recognition to image classification. Since DNNs demand a large amount of processing power, their implementation on hardware, i.e., FPGA or ASIC, has received much attention. High-level synthesis is widely used since it significantly boosts productivity and flexibility and requires minimal hardware knowledge. However, when HLS transforms a C implementation to a Register-Transfer Level one, the high parallelism capability of the FPGA is not well-utilized. HLS tools provide a feature called directives through which designers can guide the tool using some defined C pragma statements to improve performance. Nevertheless, finding appropriate directives is another challenge, which needs considerable expertise and experience. This paper proposes DeepFlexiHLS, a two-stage design space exploration flow to find a set of directives to achieve minimal latency. In the first stage, a partition-based method is used to find the directives corresponding to each partition. Aggregating all these directives leads to minimal latency. Experimental results show 54% more speed-up than similar work on VGG neural network. In the second stage, an estimator is implemented to find the latency and resource utilization of various combinations of the found directives. The results form a Pareto-frontier from which the designer can choose if FPGA resources are limited or are not to be entirely used by the DNN module.","PeriodicalId":319833,"journal":{"name":"2022 IEEE Nordic Circuits and Systems Conference (NorCAS)","volume":"33 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-10-25","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126512901","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: 0
CRC-Oriented Error Detection Architectures of Post-quantum Cryptography Niederreiter Key Generator on FPGA 基于FPGA的后量子加密密钥生成器的CRC-Oriented错误检测体系
2022 IEEE Nordic Circuits and Systems Conference (NorCAS) Pub Date : 2022-10-25 DOI: 10.1109/NorCAS57515.2022.9934378
Alvaro Cintas Canto, Mehran Mozaffari Kermani, R. Azarderakhsh, K. Gaj
{"title":"CRC-Oriented Error Detection Architectures of Post-quantum Cryptography Niederreiter Key Generator on FPGA","authors":"Alvaro Cintas Canto, Mehran Mozaffari Kermani, R. Azarderakhsh, K. Gaj","doi":"10.1109/NorCAS57515.2022.9934378","DOIUrl":"https://doi.org/10.1109/NorCAS57515.2022.9934378","url":null,"abstract":"Providing error detection constructions for Internet of nano-Things in constrained applications is of prominent importance. The Niederreiter cryptosystem falls into the category of code-based public-key cryptography. It is a relatively well-established scheme, but its key size and performance overheads have traditionally hindered its efficiency to be utilized for traditional computers. However, with the arrival of quantum computers, the Niederreiter cryptosystem is believed to be secure against attacks enabled by such computers, even though it has been previously shown that it is still vulnerable to fault injection and natural hardware defects. In this paper, we present fault detection schemes for the different blocks in the key generation of the Niederreiter cryptosystem using binary Goppa codes. These blocks perform finite field operations such as addition, multiplication, squaring, and inversion. The schemes are derived for different parameter sizes in order to have more flexibility and be able to choose according to the overheads to be tolerated and the required level of security. Moreover, we implement our fault detection schemes on Xilinx field-programmable gate array (FPGA) family Kintex UltraScale+ (device xcku5p-ffvd900-1-i) to benchmark the overhead induced of the proposed approaches.","PeriodicalId":319833,"journal":{"name":"2022 IEEE Nordic Circuits and Systems Conference (NorCAS)","volume":"116 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-10-25","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"122529815","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
Design and Exploration of an ARC-Coprocessor for LSTM Based Audio Applications 基于LSTM音频应用的arc协处理器的设计与探索
2022 IEEE Nordic Circuits and Systems Conference (NorCAS) Pub Date : 2022-10-25 DOI: 10.1109/NorCAS57515.2022.9934553
Sebastian Birke, Bjoern Hartmann, Dominik Auras, Markus G. Wloka, G. Ascheid, R. Leupers
{"title":"Design and Exploration of an ARC-Coprocessor for LSTM Based Audio Applications","authors":"Sebastian Birke, Bjoern Hartmann, Dominik Auras, Markus G. Wloka, G. Ascheid, R. Leupers","doi":"10.1109/NorCAS57515.2022.9934553","DOIUrl":"https://doi.org/10.1109/NorCAS57515.2022.9934553","url":null,"abstract":"Machine Learning (ML) techniques are applied to solve automation tasks in more and more scenarios of our daily life. For instance, Keyword Spotting applications are of interest for Internet-of-things devices in a smart home or for human-machine interaction. Different ML techniques, such as Neural Networks including Long-Short Term Memories, recently achieve reasonable accuracy above 95 % [1]. Therefore, we propose an accelerator for the Keyword spotter as a specialized coprocessor in order to retain the flexibility to fit different network structures, while the energy efficiency is increased.","PeriodicalId":319833,"journal":{"name":"2022 IEEE Nordic Circuits and Systems Conference (NorCAS)","volume":"13 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-10-25","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"121296627","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: 0
Noise Analysis of Current-Feedback DC-Servo Loop in Current-Balancing Chopper Amplifiers 电流平衡斩波放大器中电流反馈直流伺服回路的噪声分析
2022 IEEE Nordic Circuits and Systems Conference (NorCAS) Pub Date : 2022-10-25 DOI: 10.1109/NorCAS57515.2022.9934347
Yu-Kai Huang, S. Rodriguez
{"title":"Noise Analysis of Current-Feedback DC-Servo Loop in Current-Balancing Chopper Amplifiers","authors":"Yu-Kai Huang, S. Rodriguez","doi":"10.1109/NorCAS57515.2022.9934347","DOIUrl":"https://doi.org/10.1109/NorCAS57515.2022.9934347","url":null,"abstract":"Chopper amplifiers for biopotential acquisition commonly suppress differential electrode DC offsets by using a DC-servo loop (DSL). However, the noise contribution of the DSL is always neglected in noise analysis. The noise introduced by the DSL, in particular at low frequencies, is of great importance in biosensor applications. This work presents the noise modeling of a current-balancing chopper amplifier with DSL and describes the effect of the DSL on the noise performance. Two different DSL implementations are analyzed. It is found that the exact placement of the chopper in the DSL has a strong impact in the noise performance; therefore, its placement can not be arbitrarily selected. A circuit topology to minimize its noise contribution is then proposed and verified by simulation.","PeriodicalId":319833,"journal":{"name":"2022 IEEE Nordic Circuits and Systems Conference (NorCAS)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-10-25","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"127280792","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: 0
Design and Evaluation of Performance-efficient SoC-on-FPGA for Cloud-based Healthcare Applications 基于云的医疗保健应用中高性能SoC-on-FPGA的设计与评估
2022 IEEE Nordic Circuits and Systems Conference (NorCAS) Pub Date : 2022-10-25 DOI: 10.1109/NorCAS57515.2022.9934217
Mayank Kabra, P. C, M. Rao
{"title":"Design and Evaluation of Performance-efficient SoC-on-FPGA for Cloud-based Healthcare Applications","authors":"Mayank Kabra, P. C, M. Rao","doi":"10.1109/NorCAS57515.2022.9934217","DOIUrl":"https://doi.org/10.1109/NorCAS57515.2022.9934217","url":null,"abstract":"Cloud computing with more resources at disposal has served heavy computing demands for various applications. Health is one such sector where the cloud services have benefited by not only storing and updating the subscribers' health records frequently but also providing useful analytical and predictive information to the users. However most of the cloud processing runs are established on general-purpose computing devices that are non-customized for accelerating medical inferences. Hence, a special purpose and power-efficient SoC design for cloud computing targeted towards healthcare applications is desirable. The study examines the design and evaluation of SoCs for today's neural networks trained for healthcare data. The work realizes fully connected neural networks comprised of 2 and 3 layers that are trained from two freely available datasets; one meant for detecting the survival status of the individuals suffering from prostate cancer and the other for survival status post blood and marrow transplantation, respectively. Additionally, a light-weight image classifier derived from medical based MNIST pathological dataset was also considered. The three neural networks were hardware designed and characterized with two different processor cores and two extreme cache memory configurations individually and in combination to generate multiple SoC designs. Each SoC design is illustrated and evaluated in terms of power and hardware resource utilization. The SoC design incorporating all three hardware accelerators compared to the existing cloud platforms showcased power reduction by 7.13X, 5.25X, and 15X, and average throughput improvement by 49.37X, 19.78X, and 26.47X, when compared to its corresponding neural network, runs on CPU, GPU, and TPU units respectively. The SoC designs in this work with three different co-processor choices set an example to achieve customized cloud SoC designs that are power and performance efficient and targeted for healthcare applications.","PeriodicalId":319833,"journal":{"name":"2022 IEEE Nordic Circuits and Systems Conference (NorCAS)","volume":"19 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-10-25","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"131116452","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: 0
Waveform Memory for Real-Time FPGA Test of Fiber-Optic Receiver DSPs 用于光纤接收机dsp实时FPGA测试的波形存储器
2022 IEEE Nordic Circuits and Systems Conference (NorCAS) Pub Date : 2022-10-25 DOI: 10.1109/NorCAS57515.2022.9934184
Rafael Romón Sagredo, E. Börjeson, A. Mirani, M. Karlsson, P. Larsson-Edefors
{"title":"Waveform Memory for Real-Time FPGA Test of Fiber-Optic Receiver DSPs","authors":"Rafael Romón Sagredo, E. Börjeson, A. Mirani, M. Karlsson, P. Larsson-Edefors","doi":"10.1109/NorCAS57515.2022.9934184","DOIUrl":"https://doi.org/10.1109/NorCAS57515.2022.9934184","url":null,"abstract":"Verification of advanced circuit implementations poses many challenges. For complex digital signal processing (DSP) circuits, logic simulations may be prohibitively slow when non-stationary scenarios are considered. A real-time emulation technique like the Fiber-on-Chip (FoC) approach can significantly speed up DSP logic verification. However, a potential weakness with this type of emulation is that it does not use data obtained from experiments, but synthetically creates test data. We introduce a waveform memory, which can be integrated with FoC systems and similar emulators, and which allows measured waveforms to be stored and fed to DSP circuits under test. We perform real-time FPGA experiments where we evaluate a carrier-phase recovery (CPR) module that is tested using either waveform data or synthetic data. Our results for the two different data sets show that the CPR module behaves similarly, both qualitatively and quantitatively, which indicates that the synthetic phase-noise model is a valid replacement of measured data.","PeriodicalId":319833,"journal":{"name":"2022 IEEE Nordic Circuits and Systems Conference (NorCAS)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-10-25","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"121541396","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: 0
Open-Source Chip Design in Academic Education 学术教育中的开源芯片设计
2022 IEEE Nordic Circuits and Systems Conference (NorCAS) Pub Date : 2022-10-25 DOI: 10.1109/NorCAS57515.2022.9934685
Syed Anas Alam, Jakob Furbo Enevoldsen, Andreas Alkjaer Eriksen, Niels William Hartmann, Ulrik Helk, Jphirgen Kragh Jakobsen, Christa Skytte Jensen, Nicolai Dyre Bülow Jespersen, Karl Herman Krause, Mads Rumle Nordstrphim, Tjark Petersen, Luca Pezzarossa, Simon Winther Rasmussen, Martin Schoeberl, Jonas Ingerslev Sphirensen
{"title":"Open-Source Chip Design in Academic Education","authors":"Syed Anas Alam, Jakob Furbo Enevoldsen, Andreas Alkjaer Eriksen, Niels William Hartmann, Ulrik Helk, Jphirgen Kragh Jakobsen, Christa Skytte Jensen, Nicolai Dyre Bülow Jespersen, Karl Herman Krause, Mads Rumle Nordstrphim, Tjark Petersen, Luca Pezzarossa, Simon Winther Rasmussen, Martin Schoeberl, Jonas Ingerslev Sphirensen","doi":"10.1109/NorCAS57515.2022.9934685","DOIUrl":"https://doi.org/10.1109/NorCAS57515.2022.9934685","url":null,"abstract":"Chip design is usually a high-effort, high-cost, and high- risk process. However, Google has recently taken the lead to bring chip design to a level where many engineers, researchers, and even students can actively participate. In this paper, we report on a course at the Technical University of Denmark (DTU) where a group of BSc students were able to design and produce a chip using open-source tools and the SkyWater process. We present the toolchain, explain the implemented hardware architecture, and discuss the challenges encountered in the process as well as the learning values of the course. The project was finalized within one semester and has recently achieved tape-out for the next multi-project wafer manufacturing.","PeriodicalId":319833,"journal":{"name":"2022 IEEE Nordic Circuits and Systems Conference (NorCAS)","volume":"40 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-10-25","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"117256859","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
High-level Comparison of Control-Bounded A/D Converters and Continuous- Time Sigma-Delta Modulators 控制有界A/D转换器与连续时间σ - δ调制器的高级比较
2022 IEEE Nordic Circuits and Systems Conference (NorCAS) Pub Date : 2022-10-25 DOI: 10.1109/NorCAS57515.2022.9934426
Fredrik Feyling, Hampus Malmberg, C. Wulff, Hans-Andrea Loeliger, T. Ytterdal
{"title":"High-level Comparison of Control-Bounded A/D Converters and Continuous- Time Sigma-Delta Modulators","authors":"Fredrik Feyling, Hampus Malmberg, C. Wulff, Hans-Andrea Loeliger, T. Ytterdal","doi":"10.1109/NorCAS57515.2022.9934426","DOIUrl":"https://doi.org/10.1109/NorCAS57515.2022.9934426","url":null,"abstract":"In this paper, behavioural circuit simulations are used to compare the leapfrog control-bounded analog-to-digital converter to relevant continuous-time sigma-delta modulators in terms of nominal performance and sensitivity to component variations, clock jitter and finite gain-bandwidth product. Simulations show that the nominal performance of the leapfrog is similar to that of a continuous-time sigma-delta modulator of the same loop filter order and with the same number of quantization levels. Component variations in the leapfrog's analog system will introduce errors in the final output, unless the coefficients of the reconstruction filter are modified accordingly. Nevertheless, the simple, modular structure, analytical stability guarantee and single-bit quantizers make the leapfrog an interesting alternative to conventional continuous-time sigma-delta modulators.","PeriodicalId":319833,"journal":{"name":"2022 IEEE Nordic Circuits and Systems Conference (NorCAS)","volume":"19 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-10-25","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"133200438","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: 3
0
×
引用
GB/T 7714-2015
复制
MLA
复制
APA
复制
导出至
BibTeX EndNote RefMan NoteFirst NoteExpress
×
提示
您的信息不完整,为了账户安全,请先补充。
现在去补充
×
提示
您因"违规操作"
具体请查看互助需知
我知道了
×
提示
确定
请完成安全验证×
相关产品
×
本文献相关产品
联系我们:info@booksci.cn Book学术提供免费学术资源搜索服务,方便国内外学者检索中英文文献。致力于提供最便捷和优质的服务体验。 Copyright © 2023 布克学术 All rights reserved.
京ICP备2023020795号-1
ghs 京公网安备 11010802042870号
Book学术文献互助
Book学术文献互助群
群 号:604180095
Book学术官方微信
小红书