{"title":"Algorithms promoting the use of dual supply voltages for power-driven designs","authors":"C. Yeh, Min-Cheng Chang, Yin-Shuin Kang","doi":"10.1109/ARVLSI.1999.756046","DOIUrl":"https://doi.org/10.1109/ARVLSI.1999.756046","url":null,"abstract":"One recent approach for power reduction is to employ different supply voltages for different parts of a design. This paper presents optimization methods that promote the use of dual supply voltages for power-driven designs. We first propose an iterative gate sizing and voltage settling paradigm that progressively scales down the supply voltage under fixed timing constraint. Then, we propose a new physical layout style that supports dual supply voltages for cell-based designs. The new layout style can be automatically generated via a simulated annealing based placement algorithm. Experimental results using the MCNC benchmark circuits show that the proposed techniques produce very encouraging results.","PeriodicalId":358015,"journal":{"name":"Proceedings 20th Anniversary Conference on Advanced Research in VLSI","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1999-03-21","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"115000417","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 two-dimensional, object-based analog VLSI visual attention system","authors":"Charles S. Wilson, T. Morris, S. DeWeerth","doi":"10.1109/ARVLSI.1999.756055","DOIUrl":"https://doi.org/10.1109/ARVLSI.1999.756055","url":null,"abstract":"A two-dimensional object-based analog VLSI model of selective attentional processing has been implemented using a standard 1.2 /spl mu/m CMOS process. This chip extends previous work modeling object-based selection and scanning by incorporating the circuity and architectural changes necessary for two-dimensional focal plane processing. To balance the need for closely spaced large photodetectors with the space requirements of complex in-pixel processing, the chip implements a multiresolution architecture. The system has he ability to group pixels into objects; this grouping is dynamic, driven solely by the segmentation criterion at the input. In the demonstration system, image intensity has been chosen for the input saliency map and the segmentation is based on spatial lowpass filtering followed by an intensity threshold. We present experimental results.","PeriodicalId":358015,"journal":{"name":"Proceedings 20th Anniversary Conference on Advanced Research in VLSI","volume":"8 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1999-03-21","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"128574794","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":"VLSI architecture: past, present, and future","authors":"W. Dally, Steve Lacy","doi":"10.1109/ARVLSI.1999.756051","DOIUrl":"https://doi.org/10.1109/ARVLSI.1999.756051","url":null,"abstract":"This paper examines the impact of VLSI technology on the evolution of computer architecture and projects the future of this evolution. We see that over the past 20 years, the increased density of VLSI chips was applied to close the gap between microprocessors and high-end CPUs. Today this gap is fully closed and adding devices to uniprocessors is well beyond the point of diminishing returns. To continue to convert the increasing density of VLSI to computer performance we see little alternative to building multicomputers. We sketch the architecture of a VLSI multicomputer constructed from c. 2009 processor-DRAM chips and outline some of the challenges involved in building such a system. We suggest that the software transition from sequential processors to such fine-grain multicomputers can be eased by using the multicomputer as the memory system of a conventional computer.","PeriodicalId":358015,"journal":{"name":"Proceedings 20th Anniversary Conference on Advanced Research in VLSI","volume":"58 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1999-03-21","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130898335","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":"MEMS-based capacitor arrays for programmable interconnect and RF applications","authors":"B. Duewer, John M. Wilson, D. Winick, P. Franzon","doi":"10.1109/ARVLSI.1999.756061","DOIUrl":"https://doi.org/10.1109/ARVLSI.1999.756061","url":null,"abstract":"We describe a programmable capacitor technology under development at NCSU and its potential application in building programmable interconnect devices useful for system level connectivity functions, phased array beam steering and RF switching. Crossbars are made from arrays of electrostatically controlled bistable MEMS-based capacitors. These new devices allow faster signaling and consume less power than BiCMOS (or even CMOS) crossbars. We describe the essential elements of these arrays and present results obtained so far.","PeriodicalId":358015,"journal":{"name":"Proceedings 20th Anniversary Conference on Advanced Research in VLSI","volume":"34 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1999-03-21","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"114417933","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":"Clock-powered CMOS: a hybrid adiabatic logic style for energy-efficient computing","authors":"N. Tzartzanis, W. Athas","doi":"10.1109/ARVLSI.1999.756044","DOIUrl":"https://doi.org/10.1109/ARVLSI.1999.756044","url":null,"abstract":"Clock-powered logic is a new CMOS logic style which combines adiabatic switching and energy recovery-techniques with conventional CMOS logic styles for the design of low-power computing microsystems. In clock-powered logic high-capacitance nodes are adiabatically switched and powered from AC sources typically the clock lines. Low-capacitance nodes are conventionally switched and powered front a DC supply source. The clocked buffer, a CMOS structure based on bootstrapping, drives the high-capacitance nodes from the clock lines. An analytical model that closely estimates the on-resistance of the bootstrapped nFET is derived. The model is evaluated through H-SPICE simulations. Depending on the CMOS logic style used for the DC-powered blocks, pulse-to-level converters may be required to interface the clocked buffer outputs with the logic blocks. These converters inherently act as low-to-high voltage converters. Therefore, low-power operation can be achieved with clock-powered logic by both increasing the switching time and reducing the voltage swing of clock-powered nodes. This feature of clock-powered logic is evaluated through H-SPICE simulations in which the clocked buffer is compared with conventional supply-scaled CMOS drivers. The clocked buffer combined with adiabatic switching demonstrates superior energy vs. delay scalability than its supply-scaled counterparts.","PeriodicalId":358015,"journal":{"name":"Proceedings 20th Anniversary Conference on Advanced Research in VLSI","volume":"4 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1999-03-21","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"122746468","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}
T. Morris, Erica Fletcher, Cyrus Afghahi, S. Issa, K. Connolly, Jean-Charles Korta
{"title":"A column-based processing array for high-speed digital image processing","authors":"T. Morris, Erica Fletcher, Cyrus Afghahi, S. Issa, K. Connolly, Jean-Charles Korta","doi":"10.1109/ARVLSI.1999.756036","DOIUrl":"https://doi.org/10.1109/ARVLSI.1999.756036","url":null,"abstract":"We present a novel architecture for column-based image processing within an integrated CMOS sensor chip. The system includes a two-dimensional array of active pixel sensors, a one-dimensional array of analog-to-digital converters along one side of the sensor array, an array of static random access memory (SRAM) cells, and a one-dimensional array of parallel digital processing units. The architecture offers much potential for scalability, primarily due to a rotation of the digital bits coming out of the analog-to-digital converter. Each data converter produces an 8-bit value, which is then stored horizontally in an SRAM byte extending across 8 columns of pixels. This arrangement of data enables 8-bit parallel processing by each of the arithmetic logic units (ALUs), which also extends along 8 pixel columns. This grouping of 8 columns is referred to as a block-column. We describe the architecture and discuss implementation issues encountered during the design of two separate test devices fabricated in a 0.35 /spl mu/m digital CMOS process. We also present results of an architectural analysis with example algorithms.","PeriodicalId":358015,"journal":{"name":"Proceedings 20th Anniversary Conference on Advanced Research in VLSI","volume":"10 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1999-03-21","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"131568037","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":"Noise margin constraints for interconnectivity in deep submicron low power and mixed-signal VLSI circuits","authors":"Lirong Zheng, H. Tenhunen","doi":"10.1109/ARVLSI.1999.756043","DOIUrl":"https://doi.org/10.1109/ARVLSI.1999.756043","url":null,"abstract":"The continually growth in density and complexity of integrated circuits gives a difficult challenge in wireability of deep submicron VLSI circuits, particularly the advanced low power and mixed-signal ICs, where the interconnections have been seriously limited by the noise coupling problem. In this paper, we analyse the interconnectivity of advanced deep submicron low power and mixed-signal VLSI circuits under noise margin constraints. We show that noise margin constraint for signal coupling will restrict interconnect density as well as process technology options. The maximum interconnectivity, process technology options, and physical delay etc. are analysed against the noise margin constraints, for both with and without shielding wire cases. The optimal geometry and wirings for both local and global interconnects are studied with respect to noise margin, physical delay, and interconnect cross section area etc. Constraint for maximum available interconnectivity is demonstrated for interconnect wire geometry characteristics of advanced deep submicron CMOS processes. Our study reveals that, in advanced deep submicron VLSI circuit designs, interconnects should be separated functionally. Different geometries and wiring types and perhaps different fabrication flows and processes should be utilized in one chip. Some of the interconnect layers will be thus heavily dedicated such as some for local interconnects, some for intramodule interconnects, some for global wiring, and some for ground and power etc., all with optimal geometries.","PeriodicalId":358015,"journal":{"name":"Proceedings 20th Anniversary Conference on Advanced Research in VLSI","volume":"363 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1999-03-21","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"115079175","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":"Interconnect-dominated VLSI design","authors":"P. Ghosh, R. Mangaser, C. Mark, K. Rose","doi":"10.1109/ARVLSI.1999.756042","DOIUrl":"https://doi.org/10.1109/ARVLSI.1999.756042","url":null,"abstract":"This paper demonstrates the problems long, lossy wires pose for VLSI design as devices shrink to deep submicron dimensions. The degree to which both repeater insertion and reverse scaling of wire sizes are required to meet GHz clock frequency projections are estimated using a detailed wire distribution and a detailed processor model (RIPE). We also show how to achieve good floorplans with repeater insertion.","PeriodicalId":358015,"journal":{"name":"Proceedings 20th Anniversary Conference on Advanced Research in VLSI","volume":"40 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1999-03-21","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"123374194","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":"Translinear analog signal processing: a modular approach to large-scale analog computation with multiple-input translinear elements","authors":"B. Minch","doi":"10.1109/ARVLSI.1999.756048","DOIUrl":"https://doi.org/10.1109/ARVLSI.1999.756048","url":null,"abstract":"The author describes a general framework, called translinear analog signal processing (TASP), for implementing continuous-time analog signal processing systems that have a wide dynamic range and can operate with a low power-supply voltage. Such analog signal processing systems are highly modular, comprising only grounded capacitors, constant current sources, and simple circuit primitives called multiple-input translinear elements (MITEs). Moreover, the behavior of a TASP system is well described in terms of commonly used linear and nonlinear signal processing functions. Consequently, these systems should be highly amenable to behavioral-level descriptions and to computer-aided design automation techniques. The author briefly discusses the operation of MITEs and their circuit implementation. He describes the two classes of MITE circuits, MITE networks and MITE log-domain filters, that together make up the TASP framework and shows experimental data from a basic circuit from each class. The author then illustrates how we can interface these circuits in a seamless fashion to build large-scale TASP systems. Finally, he discuss the possibility of building adaptive and reconfigurable TASP systems.","PeriodicalId":358015,"journal":{"name":"Proceedings 20th Anniversary Conference on Advanced Research in VLSI","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1999-03-21","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126840981","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":"Feedback driven backtrace of analog signals and its application to circuit verification and test","authors":"R. Voorakaranam, A. Chatterjee","doi":"10.1109/ARVLSI.1999.756058","DOIUrl":"https://doi.org/10.1109/ARVLSI.1999.756058","url":null,"abstract":"This paper describes a new approach for backtracing analog signals in a circuit. The process of backtracing involves finding the input signal to an analog circuit, from knowledge of its input-output behavior and the desired output signal. While previous approaches rely on the transformation of nodal equations of the circuit to accomplish backtrace, the proposed approach derives the input signal using feedback and forward simulation of a modified circuit. Hence any commercial circuit simulator can be used to the implement the backtrace function. DC convergence conditions for the proposed backtrace approach are derived and it is shown that in the absence of hard nonlinearities, the proposed approach converges to the final solution at a quadratic rate. Application of the backtrace approach to DC verification and test of analog circuits is discussed.","PeriodicalId":358015,"journal":{"name":"Proceedings 20th Anniversary Conference on Advanced Research in VLSI","volume":"53 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1999-03-21","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126926199","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}