Pub Date : 2022-10-05DOI: 10.1109/OJSSCS.2022.3212028
Gabriele Manganaro
Increasingly wider band analog signals found in multiple information and communication technology applications, requiring real-time digital signal processing, demand analog-to-digital converters with ever higher sample rate. Several innovative techniques, from the circuit level, to architecture and algorithms, have enabled remarkable breakthroughs in a relatively short span of time. This overview article aims to introduce this topic and to point to some of the most notable results, while also highlighting open problems and engineering trends.
{"title":"An Introduction to High Sample Rate Nyquist Analog-to-Digital Converters","authors":"Gabriele Manganaro","doi":"10.1109/OJSSCS.2022.3212028","DOIUrl":"https://doi.org/10.1109/OJSSCS.2022.3212028","url":null,"abstract":"Increasingly wider band analog signals found in multiple information and communication technology applications, requiring real-time digital signal processing, demand analog-to-digital converters with ever higher sample rate. Several innovative techniques, from the circuit level, to architecture and algorithms, have enabled remarkable breakthroughs in a relatively short span of time. This overview article aims to introduce this topic and to point to some of the most notable results, while also highlighting open problems and engineering trends.","PeriodicalId":100633,"journal":{"name":"IEEE Open Journal of the Solid-State Circuits Society","volume":"2 ","pages":"82-102"},"PeriodicalIF":0.0,"publicationDate":"2022-10-05","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://ieeexplore.ieee.org/iel7/8782712/9733783/09911689.pdf","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"67868121","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2022-10-03DOI: 10.1109/OJSSCS.2022.3211482
Pieter Harpe
With the advent of small, battery-powered devices, power efficiency has become of paramount importance. For analog-to-digital converters (ADCs), the successive approximation register (SAR) architecture plays a prominent role thanks to its ability to combine power efficiency with a simple architecture, a broad application scope, and technology portability. In this review article, the basic design challenges for low-power SAR ADCs are summarized and several design techniques are illustrated. Furthermore, the limitations of SAR ADCs are outlined and hybrid architecture trends, such as noise-shaping SAR ADCs and pipelined SAR ADCs, are briefly introduced and clarified with examples.
{"title":"Low-Power SAR ADCs: Basic Techniques and Trends","authors":"Pieter Harpe","doi":"10.1109/OJSSCS.2022.3211482","DOIUrl":"https://doi.org/10.1109/OJSSCS.2022.3211482","url":null,"abstract":"With the advent of small, battery-powered devices, power efficiency has become of paramount importance. For analog-to-digital converters (ADCs), the successive approximation register (SAR) architecture plays a prominent role thanks to its ability to combine power efficiency with a simple architecture, a broad application scope, and technology portability. In this review article, the basic design challenges for low-power SAR ADCs are summarized and several design techniques are illustrated. Furthermore, the limitations of SAR ADCs are outlined and hybrid architecture trends, such as noise-shaping SAR ADCs and pipelined SAR ADCs, are briefly introduced and clarified with examples.","PeriodicalId":100633,"journal":{"name":"IEEE Open Journal of the Solid-State Circuits Society","volume":"2 ","pages":"73-81"},"PeriodicalIF":0.0,"publicationDate":"2022-10-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://ieeexplore.ieee.org/iel7/8782712/9733783/09908164.pdf","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"67868120","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
On-chip deep neural network (DNN) inference and training at the Extreme-Edge (TinyML) impose strict latency, throughput, accuracy, and flexibility requirements. Heterogeneous clusters are promising solutions to meet the challenge, combining the flexibility of DSP-enhanced cores with the performance and energy boost of dedicated accelerators. We present DARKSIDE, a System-on-Chip with a heterogeneous cluster of eight RISC-V cores enhanced with 2-b to 32-b mixed-precision integer arithmetic. To boost the performance and efficiency on key compute-intensive DNN kernels, the cluster is enriched with three digital accelerators: 1) a specialized engine for low-data-reuse depthwise convolution kernels (up to 30 MAC/cycle); 2) a minimal overhead datamover to marshal 1–32-b data on-the-fly; and 3) a 16-b floating-point tensor product engine (TPE) for tiled matrix-multiplication acceleration. DARKSIDE is implemented in 65-nm CMOS technology. The cluster achieves a peak integer performance of 65 GOPS and a peak efficiency of 835 GOPS/W when working on 2-b integer DNN kernels. When targeting floating-point tensor operations, the TPE provides up to 18.2 GFLOPS of performance or 300 GFLOPS/W of efficiency—enough to enable on-chip floating-point training at competitive speed coupled with ultralow power quantized inference.
{"title":"DARKSIDE: A Heterogeneous RISC-V Compute Cluster for Extreme-Edge On-Chip DNN Inference and Training","authors":"Angelo Garofalo;Yvan Tortorella;Matteo Perotti;Luca Valente;Alessandro Nadalini;Luca Benini;Davide Rossi;Francesco Conti","doi":"10.1109/OJSSCS.2022.3210082","DOIUrl":"https://doi.org/10.1109/OJSSCS.2022.3210082","url":null,"abstract":"On-chip deep neural network (DNN) inference and training at the Extreme-Edge (TinyML) impose strict latency, throughput, accuracy, and flexibility requirements. Heterogeneous clusters are promising solutions to meet the challenge, combining the flexibility of DSP-enhanced cores with the performance and energy boost of dedicated accelerators. We present DARKSIDE, a System-on-Chip with a heterogeneous cluster of eight RISC-V cores enhanced with 2-b to 32-b mixed-precision integer arithmetic. To boost the performance and efficiency on key compute-intensive DNN kernels, the cluster is enriched with three digital accelerators: 1) a specialized engine for low-data-reuse depthwise convolution kernels (up to 30 MAC/cycle); 2) a minimal overhead datamover to marshal 1–32-b data on-the-fly; and 3) a 16-b floating-point tensor product engine (TPE) for tiled matrix-multiplication acceleration. DARKSIDE is implemented in 65-nm CMOS technology. The cluster achieves a peak integer performance of 65 GOPS and a peak efficiency of 835 GOPS/W when working on 2-b integer DNN kernels. When targeting floating-point tensor operations, the TPE provides up to 18.2 GFLOPS of performance or 300 GFLOPS/W of efficiency—enough to enable on-chip floating-point training at competitive speed coupled with ultralow power quantized inference.","PeriodicalId":100633,"journal":{"name":"IEEE Open Journal of the Solid-State Circuits Society","volume":"2 ","pages":"231-243"},"PeriodicalIF":0.0,"publicationDate":"2022-09-27","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://ieeexplore.ieee.org/iel7/8782712/9733783/09903915.pdf","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"67868123","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2022-08-26DOI: 10.1109/OJSSCS.2022.3202145
Unbong Lee;Wanyeong Jung;Sohmyung Ha;Minkyu Je
An automatically reconfigurable switched-capacitor DC-DC converter with multiple regulated outputs is presented for wireless-powered multi-unit implantable medical devices (IMDs). In such devices, the main controller unit is powered wirelessly and provides supply voltages to the circuits of the main unit as well as multiple connected sub-units. The proposed DC-DC converter simultaneously generates two regulated voltages for the main unit and two unregulated voltages for the sub-units, which have on-site low-dropout regulators. The converter consists of i) an input-adaptive DC-DC conversion stage with two switched-capacitor (SC) DC-DC converters in series and ii) a regulating stage. In the DC-DC conversion stage, the proposed converter automatically reconfigures the conversion ratio and connection order of the two SC DC-DC converters and selects the output nodes by load selection switches depending on the input level. Thanks to these adaptive configurations, the proposed converter offers high conversion efficiencies over a wide input voltage range even with fewer flying capacitors required for the reconfigurable conversion ratios. Moreover, the selection switches are reused to regulate the output voltages to desired levels, minimizing the overhead for subsequent regulation. The IC fabricated in a 180-nm standard CMOS process achieves a conversion efficiency of 95.5% for the unregulated voltages and up to 77.4% for the regulated voltages over a wide input range of 1 V to 4 V with 0.74-mV output ripple for a load current of 20 mA, while providing four outputs (2 regulated, 2 unregulated).
{"title":"An Auto-Reconfigurable Multi-Output Regulating Switched-Capacitor DC–DC Converter for Wireless Power Reception and Distribution in Multi-Unit Implantable Devices","authors":"Unbong Lee;Wanyeong Jung;Sohmyung Ha;Minkyu Je","doi":"10.1109/OJSSCS.2022.3202145","DOIUrl":"https://doi.org/10.1109/OJSSCS.2022.3202145","url":null,"abstract":"An automatically reconfigurable switched-capacitor DC-DC converter with multiple regulated outputs is presented for wireless-powered multi-unit implantable medical devices (IMDs). In such devices, the main controller unit is powered wirelessly and provides supply voltages to the circuits of the main unit as well as multiple connected sub-units. The proposed DC-DC converter simultaneously generates two regulated voltages for the main unit and two unregulated voltages for the sub-units, which have on-site low-dropout regulators. The converter consists of i) an input-adaptive DC-DC conversion stage with two switched-capacitor (SC) DC-DC converters in series and ii) a regulating stage. In the DC-DC conversion stage, the proposed converter automatically reconfigures the conversion ratio and connection order of the two SC DC-DC converters and selects the output nodes by load selection switches depending on the input level. Thanks to these adaptive configurations, the proposed converter offers high conversion efficiencies over a wide input voltage range even with fewer flying capacitors required for the reconfigurable conversion ratios. Moreover, the selection switches are reused to regulate the output voltages to desired levels, minimizing the overhead for subsequent regulation. The IC fabricated in a 180-nm standard CMOS process achieves a conversion efficiency of 95.5% for the unregulated voltages and up to 77.4% for the regulated voltages over a wide input range of 1 V to 4 V with 0.74-mV output ripple for a load current of 20 mA, while providing four outputs (2 regulated, 2 unregulated).","PeriodicalId":100633,"journal":{"name":"IEEE Open Journal of the Solid-State Circuits Society","volume":"3 ","pages":"65-75"},"PeriodicalIF":0.0,"publicationDate":"2022-08-26","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://ieeexplore.ieee.org/iel7/8782712/10019316/09868089.pdf","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"67861768","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2022-08-11DOI: 10.1109/OJSSCS.2022.3198040
Cameron Hill;James F. Buckwalter
This work demonstrates new circuit techniques in distributed-stacked-complimentary (DiSCo) switches that enable picosecond switching speed in RF CMOS SOI switches. By using seriesstacked devices with optimized gate impedance and voltage swing, both high linearity and fast switching are possible. A theoretical analysis and design framework has been developed and verified through simulation and measurement through two broadband, high-linearity passive mixer designs, one optimized for linearity and the other for bandwidth, using a 45-nm SOI CMOS process. The mixers achieve $P_{1dB}{s}$